© 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. 63329
    Prev
    Next
    INDEX
    Explanations

    technical fields

    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
     detail
    0.61
     of
    0.59
     Detail
    0.56
     DETAIL
    0.47
    detail
    0.45
     challenge
    0.43
     invasion
    0.41
    ᅥ
    0.40
    дание
    0.40
     experiment
    0.40
    POSITIVE LOGITS
    Numerical
    0.42
     আর্থিক
    0.40
    Computational
    0.40
    ciò
    0.39
    curricular
    0.39
    Organiz
    0.39
    iological
    0.39
    alogical
    0.39
    Statistical
    0.38
     Radiological
    0.38
    Activations Density 0.008%

    No Known Activations