© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15039
    Prev
    Next
    INDEX
    Explanations

    computer hardware fixes

    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
    ---
    0.36
    _="
    0.35
    юза
    0.35
     partitions
    0.34
    hava
    0.34
     అవి
    0.34
    。。。
    0.33
    のだろう
    0.33
     ---
    0.33
    --)
    0.33
    POSITIVE LOGITS
    ftest
    0.41
     फ्रै
    0.38
     Fame
    0.38
    DAT
    0.38
     libras
    0.37
     assisted
    0.37
     abord
    0.37
    DICT
    0.37
    DICTION
    0.36
     મદદ
    0.36
    Activations Density 0.004%

    No Known Activations