© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 77415
    Prev
    Next
    INDEX
    Explanations

    model numbers

    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_53_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
    饨
    0.40
    ggle
    0.37
     Laud
    0.37
     Ви
    0.36
     ロング
    0.36
    可在
    0.36
    סף
    0.36
    本当
    0.36
    vođa
    0.35
    сий
    0.35
    POSITIVE LOGITS
    Ａ
    0.41
     выборах
    0.40
    LC
    0.39
    clidean
    0.38
    AP
    0.38
    ASC
    0.37
    PR
    0.37
     confront
    0.37
    DK
    0.36
    Ｓ
    0.36
    Activations Density 0.001%

    No Known Activations