© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164879
    Prev
    Next
    INDEX
    Explanations

    job offers and appointments

    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_31_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
    可行
    0.35
     worldly
    0.34
     conceivable
    0.33
    꺽
    0.33
     প্রদেশ
    0.32
     championship
    0.32
    ಾದರೂ
    0.31
    阻
    0.31
     Selangor
    0.30
    WI
    0.30
    POSITIVE LOGITS
    Andrea
    0.33
     Fan
    0.32
    Arrival
    0.32
     Priya
    0.31
    መሪያ
    0.31
     Gue
    0.30
    არგ
    0.30
    Fan
    0.30
     Debra
    0.30
    ಿಕ
    0.30
    Activations Density 0.001%

    No Known Activations