© 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. 59133
    Prev
    Next
    INDEX
    Explanations

    OSM

    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
    o
    2.11
    O
    1.90
     O
    1.73
     o
    1.24
     ओ
    1.09
    ו
    0.98
     О
    0.96
    ओ
    0.94
     Ο
    0.90
    و
    0.89
    POSITIVE LOGITS
    osm
    0.48
     osm
    0.47
     OSM
    0.44
    osso
    0.42
    OCT
    0.42
    osx
    0.41
    OSS
    0.40
    ії
    0.40
    ос
    0.40
    യി
    0.39
    Activations Density 0.019%

    No Known Activations