© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 213432
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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_50_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
     J
    0.45
    toe
    0.44
     Con
    0.40
     quick
    0.38
    orte
    0.37
     toe
    0.37
     workforce
    0.36
    nity
    0.36
     cous
    0.36
     الج
    0.35
    POSITIVE LOGITS
    塡
    0.42
    новні
    0.40
     Uno
    0.39
    ㄅ
    0.38
     desp
    0.38
     inactivació
    0.37
    漓
    0.37
    公子
    0.37
     paraissent
    0.37
     બો
    0.36
    Activations Density 0.002%

    No Known Activations