© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8465
    Prev
    Next
    INDEX
    Explanations

    contextual relationships in text, particularly contrasting points, competition, and game-like situations

    oai_token-act-pair · gemini-2.0-flash

    closeness

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    SerializedName
    -0.77
    脚注の使い方
    -0.77
     ISNI
    -0.72
    Vidite
    -0.71
    stateParams
    -0.65
    yntaxException
    -0.64
    Хьажоргаш
    -0.62
    PreferredItem
    -0.61
    Clik
    -0.61
    TintMode
    -0.61
    POSITIVE LOGITS
     close
    1.58
    close
    1.38
     Close
    1.25
    Close
    1.23
     CLOSE
    1.17
     closer
    1.14
     closest
    1.13
     tight
    1.04
     closely
    1.04
     closeness
    1.01
    Activations Density 1.211%

    No Known Activations