© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13736
    Prev
    Next
    INDEX
    Explanations

    code snippets or configuration parameters

    oai_token-act-pair · gemini-2.0-flash

    programming or technical terms

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

    code and technical files

    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
    Not in Any Lists

    No Comments

    Negative Logits
    endesk
    -0.52
     Consist
    -0.51
    NewGuid
    -0.50
    eclared
    -0.49
     sle
    -0.47
     testify
    -0.47
     oculto
    -0.47
    SerializedName
    -0.46
    ellem
    -0.45
    aspectj
    -0.45
    POSITIVE LOGITS
    CloseOperation
    0.69
    Kjelder
    0.66
     insuffisamment
    0.64
     stop
    0.60
     مرئيه
    0.58
    WithIOException
    0.57
     ویکی‌پدی
    0.57
     stops
    0.57
     Stop
    0.56
    Pyx
    0.55
    Activations Density 3.194%

    No Known Activations