© 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. 7956
    Prev
    Next
    INDEX
    Explanations

    month names, times, references to sports, medical terms, and legal language

    oai_token-act-pair · gemini-2.0-flash

    Dates

    np_max-act-logits · gemini-2.0-flash
    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
     Figure
    -1.88
    Figure
    -1.83
     Fig
    -1.69
    FIGURE
    -1.68
    fig
    -1.62
     FIGURE
    -1.59
     fig
    -1.52
    Fig
    -1.50
     FIG
    -1.48
    FIG
    -1.42
    POSITIVE LOGITS
    Datuak
    0.64
    weile
    0.53
     Salta
    0.50
     Winaray
    0.49
    rsiniz
    0.48
    viewDidLoad
    0.48
     gradu
    0.47
     виправивши
    0.47
     lunares
    0.46
    ,:),
    0.46
    Activations Density 8.576%

    No Known Activations