© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130753
    Prev
    Next
    INDEX
    Explanations

    venes those principles

    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_1_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
     و
    1.27
     and
    1.26
    al
    1.23
    ون
    1.18
    st
    1.07
     in
    1.06
    ،
    1.06
    ap
    1.02
    ق
    1.02
    ли
    1.00
    POSITIVE LOGITS
    CH
    1.38
    LE
    1.35
    IR
    1.30
    ↵
    1.29
    UR
    1.13
     for
    1.13
    ARE
    1.08
    ER
    1.04
    К
    1.04
    Ｍ
    1.02
    Activations Density 0.000%

    No Known Activations