© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52015
    Prev
    Next
    INDEX
    Explanations

    code block start punctuation

    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
    ♀
    0.38
    ITEM
    0.38
    uer
    0.37
    Dest
    0.37
    dotnet
    0.36
    Item
    0.36
    vVertex
    0.36
    items
    0.35
    →
    0.35
    灌
    0.35
    POSITIVE LOGITS
     morally
    0.41
     料
    0.38
     HALF
    0.37
     permisos
    0.37
     permiss
    0.36
     permis
    0.36
     Ra
    0.35
     seriously
    0.35
     licenc
    0.35
     مل
    0.35
    Activations Density 0.000%

    No Known Activations