© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4252
    Prev
    Next
    INDEX
    Explanations

    technical writing about how to play basketball or other sports

    oai_token-act-pair · gemini-2.0-flash

    ball sports

    np_max-act-logits · gemini-2.0-flash

    a/the

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     ball
    -2.41
     BALL
    -2.34
     Ball
    -2.34
    Ball
    -2.30
    ball
    -2.22
    BALL
    -2.17
     balls
    -2.13
     Balls
    -2.09
    balls
    -2.03
    Balls
    -1.95
    POSITIVE LOGITS
    multicolumn
    0.56
     nahilalakip
    0.55
    SequentialGroup
    0.54
     estimés
    0.52
    Londres
    0.47
    brooke
    0.46
     Petra
    0.46
    expandindo
    0.46
     Duque
    0.45
     Layton
    0.45
    Activations Density 1.092%

    No Known Activations