© 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. 32392
    Prev
    Next
    INDEX
    Explanations

    various aspects of self

    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
    Walls
    0.35
    貯
    0.34
    wall
    0.33
    walls
    0.33
     Walls
    0.31
     kèo
    0.31
    ")))
    0.30
    ni
    0.30
    inn
    0.30
     Toilet
    0.30
    POSITIVE LOGITS
    同比
    0.30
     cumplen
    0.30
     چاہتے
    0.30
    统计
    0.29
    upstream
    0.28
     ካ
    0.28
    зне
    0.28
    UserModel
    0.28
    しい
    0.28
     liberty
    0.27
    Activations Density 0.006%

    No Known Activations