© 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. 30812
    Prev
    Next
    INDEX
    Explanations

    pages or sheets

    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
    ஜா
    0.37
    hit
    0.29
    梅
    0.28
     دہ
    0.28
    घाटन
    0.28
    LEXPORT
    0.28
     откри
    0.28
     attaching
    0.28
     అంటున్నారు
    0.28
     promenade
    0.27
    POSITIVE LOGITS
     назначен
    0.30
     Filtration
    0.30
     页
    0.29
     gelatin
    0.29
     Messaging
    0.29
    습
    0.29
     δεδο
    0.29
    クロン
    0.28
    ansky
    0.28
    Glide
    0.28
    Activations Density 0.000%

    No Known Activations