© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220171
    Prev
    Next
    INDEX
    Explanations

    loops with i and j

    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_31_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
     finishers
    0.42
     férfi
    0.39
     newdata
    0.39
     Krakow
    0.38
     lengths
    0.37
    ជាតិ
    0.37
    <>());
    0.36
     फिर
    0.35
    ineri
    0.35
     scrat
    0.35
    POSITIVE LOGITS
    仝
    0.40
    逪
    0.39
    All
    0.37
    ২০
    0.36
    战略
    0.36
    Mix
    0.36
    Inspired
    0.36
    Minimum
    0.36
    omb
    0.35
    Always
    0.35
    Activations Density 0.001%

    No Known Activations