© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23962
    Prev
    Next
    INDEX
    Explanations

    mal

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    mM
    0.37
     Ver
    0.36
    किल
    0.36
     ছ
    0.36
    maal
    0.35
    केर
    0.35
     Webin
    0.34
    צ
    0.34
    उंड
    0.33
    Malformed
    0.33
    POSITIVE LOGITS
    beh
    0.50
    hubung
    0.46
    igned
    0.42
    hub
    0.40
    baarheid
    0.38
     समन्वय
    0.37
     Пока
    0.37
    aur
    0.37
    nut
    0.37
    ayak
    0.37
    Activations Density 0.002%

    No Known Activations