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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 5772
    Prev
    Next
    INDEX
    Explanations

    Deep dive / comprehensive overview

    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
     briefly
    0.45
    انون
    0.39
    '>");
    0.37
    Lemma
    0.36
    ostok
    0.36
    apagos
    0.35
    श्मीर
    0.34
    дентификаторы
    0.34
    $\--
    0.34
     소개해
    0.34
    POSITIVE LOGITS
     Complete
    1.40
    Complete
    1.33
     complete
    1.30
     COMPLETE
    1.25
    complete
    1.23
     completa
    1.23
    COMPLETE
    1.23
     comprehensive
    1.21
     Comprehensive
    1.20
     completo
    1.16
    Activations Density 0.648%

    No Known Activations