© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51505
    Prev
    Next
    INDEX
    Explanations

    've, 's, didn't

    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_30_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
     бойынша
    0.41
     superbe
    0.37
    Brend
    0.37
    缺少
    0.36
     lép
    0.36
     मुकेश
    0.36
    涓
    0.36
    国务
    0.36
    നു
    0.35
    ÉE
    0.34
    POSITIVE LOGITS
     Funding
    0.39
     Reforms
    0.37
     운동
    0.37
    운동
    0.35
     Kok
    0.34
     Traits
    0.34
     Wak
    0.33
    ליה
    0.33
     목표
    0.33
     गतिविधियों
    0.33
    Activations Density 0.023%

    No Known Activations