© 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. 83509
    Prev
    Next
    INDEX
    Explanations

    knight in shining armor

    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
    ל
    2.13
    ل
    2.03
    ح
    1.46
    ר
    1.41
    ur
    1.33
     in
    1.32
     to
    1.30
    在
    1.30
    面
    1.30
    all
    1.27
    POSITIVE LOGITS
    t
    2.56
    tan
    1.52
    total
    1.49
    tidak
    1.41
    st
    1.40
    town
    1.40
    ta
    1.39
    ﺼ
    1.38
    deki
    1.36
    W
    1.35
    Activations Density 0.001%

    No Known Activations