© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12572
    Prev
    Next
    INDEX
    Explanations

    words related to sports, specifically American football, including player positions, team names, and game statistics

    oai_token-act-pair · gemini-2.0-flash

    sports articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     AssemblyCulture
    -0.60
    CloseOperation
    -0.57
    enterOuterAlt
    -0.55
     صوتيه
    -0.54
    forRoot
    -0.52
    الحياه
    -0.52
    ParallelGroup
    -0.51
    CodedInputStream
    -0.50
    PLIES
    -0.49
     дописавши
    -0.49
    POSITIVE LOGITS
     vuestros
    0.54
     his
    0.52
    schrift
    0.50
    Off
    0.49
     réguli
    0.48
    interest
    0.47
     Bege
    0.47
     procedentes
    0.47
     auquel
    0.47
     headed
    0.47
    Activations Density 6.307%

    No Known Activations