© 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. 10220
    Prev
    Next
    INDEX
    Explanations

    code-related keywords/symbols from programming languages like Python.

    oai_token-act-pair · gemini-2.0-flash

    words with unusual characters or spellings

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

    code

    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
    .
    -0.49
     O
    -0.49
    Ikr
    -0.48
    łoś
    -0.47
    Editar
    -0.47
     in
    -0.47
     from
    -0.46
    amaño
    -0.46
    </td>
    -0.45
     end
    -0.45
    POSITIVE LOGITS
     Efq
    1.02
     Majefty
    0.95
     poffe
    0.93
     houſe
    0.87
    ſelf
    0.85
     perfons
    0.84
     myſelf
    0.83
     pleaſure
    0.82
     purpoſe
    0.82
     ―――――
    0.80
    Activations Density 4.387%

    No Known Activations