© 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. 11650
    Prev
    Next
    INDEX
    Explanations

    tikz and tikzmark

    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
    \}}\
    0.44
     Эн
    0.44
     envelope
    0.43
     envelopes
    0.41
    Oro
    0.39
     pover
    0.39
     Enchant
    0.38
     liu
    0.38
     En
    0.38
     Sau
    0.37
    POSITIVE LOGITS
    nahme
    0.36
     ১২শ
    0.36
    ₂,
    0.36
    瘸
    0.35
    ermal
    0.35
    ಸ್ಕೊ
    0.35
     Clk
    0.35
     ☐
    0.35
    CurrentByte
    0.35
    Diethyl
    0.34
    Activations Density 0.000%

    No Known Activations