© 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. 12439
    Prev
    Next
    INDEX
    Explanations

    words related to lists and items in a collection

    oai_token-act-pair · gemini-2.0-flash

    clubs

    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
     propOrder
    -0.69
     LoggerFactory
    -0.66
     requestCode
    -0.64
    tetés
    -0.63
    aarrggbb
    -0.63
    InputBorder
    -0.59
    WebElementEntity
    -0.58
     protoimpl
    -0.57
    Билгалдахарш
    -0.56
     uVar
    -0.56
    POSITIVE LOGITS
     club
    0.93
    club
    0.87
     Club
    0.78
    Club
    0.73
     CLUB
    0.72
    CLUB
    0.70
     clubs
    0.69
     klub
    0.69
    clubs
    0.64
     Clubs
    0.61
    Activations Density 2.988%

    No Known Activations