© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32655
    Prev
    Next
    INDEX
    Explanations

    Fg%

    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_40_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
    Tie
    0.42
    ┴
    0.40
    XD
    0.39
    릿
    0.39
    breakers
    0.38
     Tie
    0.36
     অবন
    0.36
    izards
    0.35
    Path
    0.35
    Tonight
    0.35
    POSITIVE LOGITS
     curv
    0.38
     feme
    0.37
    AGN
    0.37
    搜
    0.37
    ূন্য
    0.36
     曲
    0.36
     goog
    0.36
     உ
    0.36
     eating
    0.35
     settlement
    0.35
    Activations Density 0.002%

    No Known Activations