Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 12082
    Prev
    Next
    INDEX
    Explanations

    text related to football games in the NFL

    oai_token-act-pair · gemini-2.0-flash

    Football games

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    <bos>
    -0.63
    MigrationBuilder
    -0.56
    RuleContext
    -0.56
     ngan
    -0.52
    casian
    -0.52
    teness
    -0.52
     Recre
    -0.49
    󠁢
    -0.49
     Elise
    -0.48
    alto
    -0.48
    POSITIVE LOGITS
    SourceChecksum
    0.70
    routeProvider
    0.59
     مرئيه
    0.59
    TagMode
    0.58
     makeStyles
    0.53
    LEncoder
    0.53
     famí
    0.52
    $_.
    0.50
     Վերցված
    0.50
    ();?>
    0.50
    Activations Density 2.251%

    No Known Activations