© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10985
    Prev
    Next
    INDEX
    Explanations

    short clauses, perhaps fragments, ending with a period

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    Datuak
    -0.57
    rawDesc
    -0.57
    QMetaType
    -0.48
    ItemBackground
    -0.47
     Gert
    -0.47
     gynnwys
    -0.47
    PROTOBUF
    -0.43
     gæ
    -0.43
     doth
    -0.43
    出版年
    -0.42
    POSITIVE LOGITS
     createSprite
    0.73
    Демографія
    0.70
    aarrggbb
    0.68
     comuniques
    0.62
     “
    0.58
    անո
    0.53
     "
    0.53
     Púb
    0.53
     Madhya
    0.52
    󠁢
    0.52
    Activations Density 1.135%

    No Known Activations