© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175089
    Prev
    Next
    INDEX
    Explanations

    quarter

    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_20_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
     girl
    0.37
     বয়স্ক
    0.35
    Sprintf
    0.34
     ልጅ
    0.34
    𒋛
    0.33
    ષ્ય
    0.33
     পরীক্ষা
    0.33
    лями
    0.33
     Pá
    0.33
     Wilkinson
    0.32
    POSITIVE LOGITS
    că
    0.38
    pcid
    0.35
    amm
    0.34
    づ
    0.34
    cate
    0.33
     seemingly
    0.32
    destination
    0.32
    amt
    0.32
    kai
    0.31
     statically
    0.31
    Activations Density 0.000%

    No Known Activations