© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161011
    Prev
    Next
    INDEX
    Explanations

    verus, verilog, version

    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_2_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
    は
    1.05
    ۔
    0.97
    y
    0.93
    는
    0.92
    是
    0.86
    ে
    0.83
    i
    0.81
    לי
    0.70
    并
    0.67
    ou
    0.66
    POSITIVE LOGITS
    л
    0.96
    ков
    0.73
    ل
    0.73
    ק
    0.73
     have
    0.72
     Waver
    0.71
    st
    0.70
    te
    0.70
    лло
    0.68
    vg
    0.66
    Activations Density 0.002%

    No Known Activations