© 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. 146393
    Prev
    Next
    INDEX
    Explanations

    code terms

    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
     :
    0.48
     byt
    0.38
    昊
    0.38
    so
    0.37
     $:
    0.37
    $:
    0.36
     poput
    0.36
     :"
    0.36
    the
    0.35
    ুদ্ধে
    0.35
    POSITIVE LOGITS
     Time
    0.46
     Function
    0.45
     print
    0.44
     Services
    0.42
     Public
    0.42
     Utilization
    0.42
     Silent
    0.42
     Eb
    0.41
    Aren
    0.41
     Was
    0.40
    Activations Density 0.001%

    No Known Activations