© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11552
    Prev
    Next
    INDEX
    Explanations

    words related to playing video games, especially role playing games

    oai_token-act-pair · gemini-2.0-flash

    about games

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    complexType
    -0.60
    ゴリー
    -0.55
    MainThread
    -0.52
    GeneratedCode
    -0.51
    üyada
    -0.51
    addGroup
    -0.51
     cré
    -0.50
     noDo
    -0.49
    ConstraintMaker
    -0.48
    cill
    -0.48
    POSITIVE LOGITS
     متعلقه
    0.75
     rhythm
    0.61
     OGS
    0.56
     AssemblyTitle
    0.53
    persona
    0.51
    rhythm
    0.51
     XY
    0.51
    fold
    0.51
     AutoMapper
    0.51
     folds
    0.50
    Activations Density 5.188%

    No Known Activations