© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3690
    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_5_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
    ական
    1.68
    ulously
    1.65
    ท์
    1.59
    t
    1.56
    тельными
    1.55
    referenced
    1.54
    मै
    1.54
    //
    1.52
    檛
    1.50
    А
    1.50
    POSITIVE LOGITS
     willingly
    1.89
    ek
    1.89
     forthcoming
    1.89
     sporadically
    1.88
     beg
    1.87
     gladly
    1.86
     Kollegen
    1.85
     harass
    1.83
     Также
    1.82
    et
    1.81
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.