© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214226
    Prev
    Next
    INDEX
    Explanations

    medulla,CHARGE,qt,Square,foreign

    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_5_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
    in
    1.84
    os
    1.24
    et
    1.20
    at
    1.16
    inę
    1.14
    h
    1.11
    dır
    1.06
    oft
    1.05
    i
    1.03
    by
    1.02
    POSITIVE LOGITS
    ہ
    1.19
     is
    1.15
    ți
    1.05
     hostage
    1.00
     sanitized
    0.99
    ות
    0.97
    ти
    0.95
    있
    0.95
    ین
    0.92
    ห
    0.89
    Activations Density 0.000%

    No Known Activations