© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63154
    Prev
    Next
    INDEX
    Explanations

    verbatim reproduction

    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
     paraphr
    1.41
     paraphrase
    1.38
     verbatim
    1.36
    原文
    0.96
    aphr
    0.44
     Frida
    0.43
    转载
    0.43
    摘
    0.39
     displaced
    0.38
     snork
    0.36
    POSITIVE LOGITS
    ver
    1.30
    par
    1.12
     Ver
    1.02
     ver
    0.96
    Ver
    0.92
    Par
    0.80
    VER
    0.71
     par
    0.69
     VER
    0.61
    PAR
    0.61
    Activations Density 0.006%

    No Known Activations