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-3-4B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 9244
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </h5>
    0.89
    </h3>
    0.82
    </th>
    0.81
    </span>
    0.79
    </u>
    0.75
    Folder
    0.75
    Online
    0.73
    Pen
    0.73
    </caption>
    0.72
    Navigation
    0.72
    POSITIVE LOGITS
    лях
    0.70
    ших
    0.67
    вих
    0.65
     RATES
    0.62
    ports
    0.62
     rocky
    0.61
     специальных
    0.60
     cones
    0.60
     Aka
    0.60
    зера
    0.60
    Activations Density 0.030%

    No Known Activations