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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11689
    Prev
    Next
    INDEX
    Explanations

    text that is part of an online marketing or technology white paper

    oai_token-act-pair · gemini-2.0-flash

    rare or archaic words

    np_token-act-pair-logits · gpt-4o-mini
    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
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.89
     da
    -0.85
     d
    -0.77
     here
    -0.77
     and
    -0.74
     sa
    -0.74
     (
    -0.73
     don
    -0.73
     la
    -0.72
     in
    -0.71
    POSITIVE LOGITS
     itſelf
    1.59
     Diſ
    1.53
     Anſ
    1.51
     Reſ
    1.45
     Monfieur
    1.45
     Shakspeare
    1.40
     pleaſure
    1.39
     Jefus
    1.38
     Houſe
    1.38
    ſelf
    1.38
    Activations Density 2.110%

    No Known Activations