© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108187
    Prev
    Next
    INDEX
    Explanations

    LMSYS

    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_2_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
    ע
    1.23
    その
    1.16
    ל
    1.11
    ী
    1.09
    ور
    1.09
    یر
    1.06
    ן
    1.05
    ную
    1.05
    یت
    1.04
    یم
    1.03
    POSITIVE LOGITS
    ’
    1.22
    ب
    1.19
    st
    1.09
    కు
    0.96
    ma
    0.95
    stion
    0.89
    flächen
    0.88
    ja
    0.87
    r
    0.86
    s
    0.86
    Activations Density 0.001%

    No Known Activations