© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122950
    Prev
    Next
    INDEX
    Explanations

    domestic terrorism and sphere

    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_3_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
    a
    1.23
    ه
    1.15
    ing
    1.11
    h
    1.09
    in
    1.05
    ch
    1.02
    o
    0.99
    :
    0.98
    an
    0.95
    es
    0.93
    POSITIVE LOGITS
     ನಿಜ
    0.72
    ﻡ
    0.68
    ﺫ
    0.67
     יש
    0.66
    ﺭ
    0.66
     Под
    0.66
     Бра
    0.66
     გა
    0.65
     Бар
    0.65
     Ори
    0.64
    Activations Density 0.002%

    No Known Activations