© 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. 3424
    Prev
    Next
    INDEX
    Explanations

    words that often occur in sports articles or news, especially those related to teams and players

    oai_token-act-pair · gemini-2.0-flash

    from

    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
    MigrationBuilder
    -0.63
    TabIndex
    -0.57
     catena
    -0.52
    DeleteBehavior
    -0.51
    +#+
    -0.49
     ureter
    -0.48
     notations
    -0.47
    存于互联网档案馆
    -0.47
    openqa
    -0.47
    Coast
    -0.47
    POSITIVE LOGITS
    __'
    0.57
    UnifiedTopology
    0.52
    NewUrlParser
    0.52
    észetes
    0.52
     >=",
    0.51
    aarrggbb
    0.51
     trouverez
    0.50
    ">//
    0.50
     devriez
    0.50
    '}}
    0.50
    Activations Density 0.405%

    No Known Activations