© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4414
    Prev
    Next
    INDEX
    Explanations

    code-related tokens such as function names, io operations, flags, and file operations

    oai_token-act-pair · gemini-2.0-flash

    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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     disambiguazione
    -0.93
    يكب
    -0.84
    aarrggbb
    -0.84
    CppMethod
    -0.82
    featureID
    -0.73
    endphp
    -0.71
    Manbalar
    -0.71
    WebServlet
    -0.69
    ViewFeatures
    -0.68
     متعلقه
    -0.67
    POSITIVE LOGITS
    0.45
    6
    0.44
     HasFactory
    0.43
     habet
    0.39
    </
    0.36
    ็อ
    0.35
     tendre
    0.35
    aloo
    0.34
    あれ
    0.33
     ابن
    0.33
    Activations Density 17.544%

    No Known Activations