© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 1481
    Prev
    Next
    INDEX
    Explanations

    persuasion, hooks, initiating change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_38_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
     displacing
    0.38
     attribu
    0.37
     گا
    0.36
     eccentricity
    0.36
    潴
    0.36
    世話
    0.36
     тяже
    0.36
     instância
    0.36
     ಮ
    0.35
     Dön
    0.35
    POSITIVE LOGITS
    Seth
    0.41
    PU
    0.41
     spanish
    0.40
     CSP
    0.40
    idee
    0.40
    MW
    0.39
    ﹍
    0.38
    VOL
    0.38
    рес
    0.38
    Vi
    0.38
    Activations Density 0.101%

    No Known Activations