© 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. 166528
    Prev
    Next
    INDEX
    Explanations

    bring down the next

    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
     LID
    0.37
    SizeType
    0.37
    选
    0.37
     compar
    0.36
     homogeneous
    0.36
     discriminant
    0.36
     escolh
    0.36
     actual
    0.36
     numberWith
    0.36
    舌
    0.36
    POSITIVE LOGITS
     брон
    0.40
     Dive
    0.38
     камера
    0.38
     พา
    0.38
     kin
    0.36
     Silk
    0.36
     тка
    0.36
    Loren
    0.36
     Lore
    0.35
     марке
    0.35
    Activations Density 0.000%

    No Known Activations