© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3197
    Prev
    Next
    INDEX
    Explanations

    words related to sports or hobbies, often associated with numbers

    oai_token-act-pair · gemini-2.0-flash

    game, sport, activity

    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
    Races
    -0.87
     ostavi
    -0.85
    SequentialGroup
    -0.83
     Races
    -0.80
     races
    -0.79
     diseases
    -0.79
     wars
    -0.77
     cancers
    -0.76
     dances
    -0.75
     games
    -0.73
    POSITIVE LOGITS
     game
    0.69
     sport
    0.66
     Krankheit
    0.63
     disease
    0.59
     ziekte
    0.58
    game
    0.56
     fishery
    0.52
     gioco
    0.50
     activity
    0.49
    原始内容存档于
    0.49
    Activations Density 10.952%

    No Known Activations