© 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. 146982
    Prev
    Next
    INDEX
    Explanations

    than

    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
     =
    0.52
     a
    0.50
     $=$
    0.49
     albumin
    0.47
    albumin
    0.41
    
    0.40
     ===========
    0.39
     kuin
    0.39
     an
    0.39
     peritone
    0.39
    POSITIVE LOGITS
    /
    0.83
    ／
    0.65
     /
    0.62
    /<
    0.54
     Less
    0.50
    Less
    0.50
    Least
    0.48
    _/
    0.48
    /}
    0.47
    /-
    0.46
    Activations Density 0.002%

    No Known Activations