© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80595
    Prev
    Next
    INDEX
    Explanations

    list items

    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
    樹
    0.03
    груп
    0.03
    UserName
    0.03
    早
    0.03
    Rectangle
    0.03
    群
    0.03
    ouched
    0.03
     توانائی
    0.03
     ゼ
    0.03
     '>'
    0.03
    POSITIVE LOGITS
    绾
    0.04
     Kont
    0.03
     kont
    0.03
    頫
    0.03
    माही
    0.03
    erné
    0.03
    дный
    0.03
    Pooled
    0.03
     MOR
    0.03
    oldown
    0.03
    Activations Density 0.005%

    No Known Activations