© 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. 80564
    Prev
    Next
    INDEX
    Explanations

    code block separator

    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
     ऑफर
    0.38
     ഇഷ്ട
    0.38
     justific
    0.37
     drafted
    0.37
    Ф
    0.37
    ᄅ
    0.37
     Pharmacol
    0.37
     Flame
    0.37
     NIN
    0.36
     nice
    0.36
    POSITIVE LOGITS
    service
    0.35
     Gibson
    0.35
    aty
    0.34
    Uppercase
    0.33
    Gibson
    0.33
    궤
    0.33
    మన్
    0.32
    デン
    0.32
    zó
    0.32
    xy
    0.32
    Activations Density 0.000%

    No Known Activations