© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 152264
    Prev
    Next
    INDEX
    Explanations

    say "soluble"

    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_60_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
    的可
    0.55
    可
    0.54
     قابل
    0.49
     可
    0.44
     Interest
    0.41
     exploration
    0.41
     edible
    0.38
     Payable
    0.38
    {}\
    0.37
     Wages
    0.37
    POSITIVE LOGITS
     so
    0.68
    symmetric
    0.51
     symmetric
    0.49
     soooo
    0.48
     sagitt
    0.47
     convexe
    0.46
    sounding
    0.45
     inhomogeneous
    0.45
    så
    0.44
     covariant
    0.43
    Activations Density 0.000%

    No Known Activations