© 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-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 229361
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     மா
    0.39
     eût
    0.38
    estry
    0.38
     ย
    0.37
    idden
    0.37
    நாட்டு
    0.36
     ای
    0.36
    ارڈ
    0.36
     اید
    0.36
    attle
    0.35
    POSITIVE LOGITS
    َه
    0.45
    ِه
    0.44
    ﮭ
    0.44
    etan
    0.43
    ئه
    0.41
     h
    0.40
     sie
    0.40
     Mene
    0.39
    悌
    0.39
     Kald
    0.39
    Activations Density 0.000%

    No Known Activations