© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 205570
    Prev
    Next
    INDEX
    Explanations

    say meters

    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_56_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
     ม
    0.75
     M
    0.73
     ம
    0.67
     الم
    0.66
    M
    0.63
    М
    0.63
    ﾏ
    0.63
    𝑀
    0.63
     המ
    0.62
     М
    0.61
    POSITIVE LOGITS
     races
    0.42
     şey
    0.39
    زع
    0.37
     combats
    0.37
    字节
    0.37
    জন্য
    0.35
     freedoms
    0.35
     Alonzo
    0.35
    swadian
    0.35
    징
    0.35
    Activations Density 0.003%

    No Known Activations