© 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. 214961
    Prev
    Next
    INDEX
    Explanations

    cox proportional hazards

    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
    r
    1.36
    c
    1.27
    rda
    1.22
    em
    1.20
    <0x0D>
    1.12
    एस
    1.10
    l
    1.09
    t
    1.06
    s
    1.05
    triggered
    1.02
    POSITIVE LOGITS
    ן
    1.05
    ל
    1.04
    א
    1.04
    ور
    1.03
    وك
    1.01
    ا
    0.98
    اد
    0.98
    ע
    0.95
    的時間
    0.93
    in
    0.91
    Activations Density 0.000%

    No Known Activations