© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9053
    Prev
    Next
    INDEX
    Explanations

    words frequently used to describe football players and game play

    oai_token-act-pair · gemini-2.0-flash

    terms related to football positions or plays

    np_token-act-pair-logits · gpt-4o-mini

    Football receivers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ThroughAttribute
    -0.89
    stateProvider
    -0.84
    webElementXpaths
    -0.82
    MigrationBuilder
    -0.72
    AddTagHelper
    -0.72
    TintMode
    -0.72
     vPvB
    -0.71
    |}{$
    -0.71
    routeProvider
    -0.71
    Demografie
    -0.71
    POSITIVE LOGITS
    Portail
    0.53
     wide
    0.44
    cet
    0.43
    SequentialGroup
    0.43
    char
    0.43
    եռ
    0.42
     Char
    0.41
    存于互联网档案馆
    0.41
     receiving
    0.40
    振
    0.40
    Activations Density 0.567%

    No Known Activations