© 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-3-4B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 260
    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_12_width_16k_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
     chooses
    0.41
     chose
    0.40
    trying
    0.37
     costitu
    0.35
    If
    0.34
    ...";
    0.33
     —,
    0.33
     რ
    0.33
     corresponds
    0.33
    Filling
    0.33
    POSITIVE LOGITS
     Veteran
    0.40
     Veterinary
    0.39
    irled
    0.38
    aların
    0.37
    veter
    0.37
     Newsletter
    0.37
     Veterans
    0.36
    者の
    0.35
    uparrow
    0.35
    شش
    0.35
    Activations Density 0.003%

    No Known Activations