© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 211971
    Prev
    Next
    INDEX
    Explanations

    proven method or solution

    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_19_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
    WIDE
    0.46
    IRA
    0.46
     مختلفة
    0.46
     Christophe
    0.43
    rapie
    0.43
    wallpaper
    0.42
     WHERE
    0.42
     広
    0.41
    omega
    0.40
    dove
    0.40
    POSITIVE LOGITS
     público
    0.50
     emoc
    0.45
     līdz
    0.44
    ילים
    0.43
     Traditions
    0.43
     Sorrow
    0.43
    ູ່
    0.42
    高于
    0.42
     juegan
    0.42
     Heritage
    0.42
    Activations Density 0.001%

    No Known Activations