© 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. 111577
    Prev
    Next
    INDEX
    Explanations

    form html tags

    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
    s
    1.55
     at
    1.32
     and
    1.16
    ۵
    1.16
    ের
    1.13
    ру
    1.10
    いる
    1.09
    ς
    1.06
    ओं
    1.02
     is
    1.01
    POSITIVE LOGITS
    ع
    1.92
    ת
    1.16
    ak
    1.11
    ש
    1.11
    ت
    1.09
    gli
    1.05
    т
    1.05
    ли
    1.03
    ك
    1.02
     zaji
    1.01
    Activations Density 0.001%

    No Known Activations