© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80096
    Prev
    Next
    INDEX
    Explanations

    proclamation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    ↵↵
    1.93
    i
    1.60
    ી
    1.42
     to
    1.40
    ి
    1.30
     I
    1.27
     and
    1.25
    ?
    1.23
    y
    1.20
    ে
    1.15
    POSITIVE LOGITS
    م
    2.08
    ر
    1.95
    न
    1.75
    ن
    1.69
    ন
    1.64
    لية
    1.62
    ش
    1.50
    ج
    1.46
    น
    1.41
    ین
    1.40
    Activations Density 0.001%

    No Known Activations