© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 154113
    Prev
    Next
    INDEX
    Explanations

    steps

    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_60_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
    ８
    0.57
    ᱘
    0.56
    ᱗
    0.53
    8
    0.52
    ٧
    0.50
    ７
    0.49
     eighty
    0.48
    ⁸
    0.46
    ೭
    0.45
     revenues
    0.44
    POSITIVE LOGITS
    (#
    0.52
     (#
    0.49
     #
    0.48
     `#
    0.48
     \#
    0.46
     Twenty
    0.45
     "#
    0.45
     Five
    0.45
     і
    0.44
    五十
    0.44
    Activations Density 0.001%

    No Known Activations