© 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. 92234
    Prev
    Next
    INDEX
    Explanations

    mixed language and numbers

    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
    ٦
    1.02
    ٥
    0.95
    ٤
    0.94
     ٢
    0.89
     ١
    0.88
    ٢
    0.82
    ４
    0.81
    ٧
    0.81
    １
    0.81
    ８
    0.81
    POSITIVE LOGITS
     occur
    0.44
     occurred
    0.43
    ৯০
    0.39
    ovsk
    0.39
    ৪৪
    0.39
     ocorrer
    0.38
    ৩৩
    0.38
    ornis
    0.38
    ukar
    0.37
    ৩৬
    0.37
    Activations Density 0.009%

    No Known Activations