© 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. 195788
    Prev
    Next
    INDEX
    Explanations

    write article

    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
     کردند
    0.43
    栱
    0.42
     کنند
    0.41
    徘
    0.40
    诵
    0.39
     সংস্কৃতি
    0.39
     суу
    0.39
    瀋
    0.39
     buddh
    0.38
    ಸೂ
    0.37
    POSITIVE LOGITS
    Mobs
    0.39
     tips
    0.39
    @-
    0.37
    .”)
    0.35
    イナー
    0.35
     ARTICLE
    0.35
     identifier
    0.34
    好的
    0.34
    ARTICLE
    0.34
    AE
    0.34
    Activations Density 0.000%

    No Known Activations