© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 137942
    Prev
    Next
    INDEX
    Explanations

    email templates

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    hnt
    0.46
     Noting
    0.42
     ರೆ
    0.41
     ර
    0.40
     Nota
    0.40
    േഷ
    0.38
    اسي
    0.38
     oxidation
    0.36
    addition
    0.36
     দ্র
    0.36
    POSITIVE LOGITS
     услуг
    0.38
    平
    0.37
    될
    0.37
    となる
    0.37
    sns
    0.36
    ulele
    0.36
     चंदन
    0.36
    തമായ
    0.36
    SDD
    0.36
    되는
    0.35
    Activations Density 0.003%

    No Known Activations