© 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. 58031
    Prev
    Next
    INDEX
    Explanations

    os

    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
     leichter
    0.54
     einfacher
    0.49
     ."
    0.43
    ILITIES
    0.41
     .
    0.41
    .??.??"]
    0.40
    ./
    0.39
     .)
    0.39
     easier
    0.38
     moderator
    0.38
    POSITIVE LOGITS
     ou
    0.38
    >=</
    0.38
    $=\
    0.37
    pace
    0.36
    car
    0.36
    need
    0.35
    fluid
    0.35
    Compatibility
    0.35
    Compat
    0.35
     need
    0.34
    Activations Density 0.000%

    No Known Activations