© 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. 7593
    Prev
    Next
    INDEX
    Explanations

    computer code syntax, especially characters used in conditional statements ("if", "else", "fi").

    oai_token-act-pair · gemini-2.0-flash

    programming code keywords and languages

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

    Code, conditional statements

    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
    ')";
    -0.63
     beginning
    -0.62
    ')"
    -0.59
    ')")
    -0.54
     begin
    -0.52
    ))[
    -0.52
    ")]
    -0.51
     end
    -0.51
    ))]
    -0.49
     ")";
    -0.49
    POSITIVE LOGITS
    enumii
    0.65
     חיצוניים
    0.63
    HtmlAttribute
    0.58
     démocr
    0.57
     doInBackground
    0.56
    ConstraintMaker
    0.56
    ειτουργ
    0.56
     keten
    0.55
     ویکی‌پدیای
    0.53
    PerformLayout
    0.52
    Activations Density 1.188%

    No Known Activations