© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12912
    Prev
    Next
    INDEX
    Explanations

    miscellaneous headers, disclaimers, and legal language

    oai_token-act-pair · gemini-2.0-flash

    specialized legal or formal terms

    np_token-act-pair-logits · gpt-4o-mini

    Code or legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    •the_software_is_provided_"as:a019a833-837d-5856-ba72-b7f81f2e9c66:gemma-2-2b:gemmascope-transcoder-16k
    Top frequency features for prompt

    No Comments

    Negative Logits
     iprot
    -0.75
     JADX
    -0.69
    
    -0.69
    TypedDataSet
    -0.68
     cioè
    -0.67
     dAtA
    -0.66
     spirituale
    -0.66
     ویکی‌پدی
    -0.66
     саны
    -0.66
    AlterField
    -0.65
    POSITIVE LOGITS
    CHREIB
    0.50
    /*
    0.49
     DEPOSITORY
    0.46
     PICTOGRAM
    0.40
    VIRONMENT
    0.39
     CALIFORNI
    0.38
    IBLES
    0.37
      (
    0.36
     HIEROGLYPH
    0.35
    CHREIBUNG
    0.35
    Activations Density 1.148%

    No Known Activations