© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 141906
    Prev
    Next
    INDEX
    Explanations

    brace yourself

    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_0_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
    3.23
    t
    2.72
    i
    2.08
    r
    2.08
    to
    1.98
    ,
    1.93
    u
    1.79
    m
    1.76
    st
    1.73
    l
    1.70
    POSITIVE LOGITS
    ри
    1.51
    те
    1.48
    এম
    1.38
    هم
    1.32
    ен
    1.31
     وي
    1.31
    ку
    1.30
    ード
    1.30
    ам
    1.30
    ફેદ
    1.30
    Activations Density 0.000%

    No Known Activations