© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108442
    Prev
    Next
    INDEX
    Explanations

    hows

    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_2_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
    ו
    1.71
    ↵↵
    1.48
    л
    1.34
    ী
    1.30
    다
    1.29
    in
    1.19
    ש
    1.17
    ar
    1.16
    ল
    1.16
    ো
    1.16
    POSITIVE LOGITS
    g
    1.59
    d
    1.55
    কে
    1.28
    dna
    1.27
    １
    1.11
     toán
    1.08
    る
    1.08
    เป็น
    1.07
    gf
    1.07
    dienst
    1.06
    Activations Density 0.002%

    No Known Activations