© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 59329
    Prev
    Next
    INDEX
    Explanations

    code/symbols

    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_59_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
    }/
    0.32
     Frontiers
    0.31
    억
    0.31
    }$
    0.31
     Middlesex
    0.30
    戊
    0.30
    )$-
    0.29
    濱
    0.29
    ./
    0.29
    imum
    0.29
    POSITIVE LOGITS
    idCliente
    0.42
     문제입니다
    0.42
    ក្នុងការ
    0.42
    mAb
    0.40
    __["
    0.40
    sqlUpdate
    0.39
     topLine
    0.38
    再去
    0.38
     —¿
    0.38
     изо
    0.38
    Activations Density 0.236%

    No Known Activations