© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12406
    Prev
    Next
    INDEX
    Explanations

    code blocks with indentation or returns

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    j
    -0.56
    frameCount
    -0.52
    i
    -0.47
    l
    -0.47
    الإنجليزية
    -0.46
    te
    -0.46
     olhos
    -0.45
    シ
    -0.45
    omni
    -0.45
    World
    -0.44
    POSITIVE LOGITS
    interopRequire
    0.81
    nodoc
    0.80
    NewUrlParser
    0.76
     متعلقه
    0.71
    NUMX
    0.70
    endphp
    0.69
    MLLoader
    0.69
    uaire
    0.67
    extAlignment
    0.66
     Drapeau
    0.66
    Activations Density 1.516%

    No Known Activations