© 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. 4192
    Prev
    Next
    INDEX
    Explanations

    C preprocessor directives

    oai_token-act-pair · gemini-2.0-flash

    numerical or symbolic code patterns

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

    #

    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
    tanleria
    -0.79
    kuuta
    -0.77
    webElementXpaths
    -0.73
    PhysRevD
    -0.73
    Personendaten
    -0.69
    RenderAtEndOf
    -0.68
     "..\..\..\
    -0.66
    ьаж
    -0.66
    AsUp
    -0.66
    featureID
    -0.64
    POSITIVE LOGITS
     mẫu
    0.43
    vre
    0.41
     morrow
    0.41
     >=",
    0.41
    lý
    0.40
    แน่น
    0.39
     แห
    0.39
    mbres
    0.39
     Biar
    0.36
    endregion
    0.36
    Activations Density 0.486%

    No Known Activations