© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10750
    Prev
    Next
    INDEX
    Explanations

    words associated with playing a game and collaborating with others in that game

    oai_token-act-pair · gemini-2.0-flash

    say "play"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    
    -0.77
    brainly
    -0.76
    GEBURTSDATUM
    -0.71
    +#+#
    -0.67
     <=",
    -0.66
    ]--;
    -0.63
    RenderAtEndOf
    -0.63
     Municipalidad
    -0.61
     ModelExpression
    -0.60
    hability
    -0.58
    POSITIVE LOGITS
     play
    0.55
     played
    0.53
     plays
    0.50
     Rendez
    0.49
     PLAY
    0.49
     walk
    0.49
     pick
    0.49
     trigger
    0.49
     Extragalactic
    0.48
    play
    0.47
    Activations Density 2.930%

    No Known Activations