© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9359
    Prev
    Next
    INDEX
    Explanations

    instances of people wanting the ability to do something

    oai_token-act-pair · gemini-2.0-flash

    Programming/technical discussions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    <bos>
    -0.51
     nahilalakip
    -0.51
     дописавши
    -0.50
    ArrowToggle
    -0.48
    continues
    -0.48
     ""],
    -0.48
     незавершена
    -0.45
     continues
    -0.45
     كمان
    -0.44
    WEBPACK
    -0.44
    POSITIVE LOGITS
    ConstraintMaker
    0.73
    IntoConstraints
    0.67
     purpoſe
    0.59
     ſtate
    0.57
    ResponseWriter
    0.57
    PhysRev
    0.57
    exitRule
    0.56
    最快更新
    0.56
     FetchType
    0.54
     TextAlign
    0.54
    Activations Density 4.567%

    No Known Activations