© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13956
    Prev
    Next
    INDEX
    Explanations

    instances of communication/conversations

    oai_token-act-pair · gemini-2.0-flash

    Conflict/requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     responded
    -0.49
     elicited
    -0.48
     giggled
    -0.48
     reaction
    -0.48
    jdons
    -0.47
     reactions
    -0.47
     giggle
    -0.46
     reacted
    -0.45
    eval
    -0.44
    anyway
    -0.44
    POSITIVE LOGITS
     صوتيه
    0.79
    BeginInit
    0.77
    RectangleBorder
    0.74
    fillType
    0.73
    الإنجليزية
    0.71
    ViewImports
    0.71
    IntoConstraints
    0.70
     يتيمه
    0.66
    يميديا
    0.66
     StatefulWidget
    0.64
    Activations Density 0.448%

    No Known Activations