© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 4384
    Prev
    Next
    INDEX
    Explanations

    choco

    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_38_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
    bulb
    0.37
    wald
    0.37
    thor
    0.36
     హో
    0.34
     NSCs
    0.34
     दीवार
    0.34
    databind
    0.34
    筤
    0.34
    stav
    0.33
     дү
    0.33
    POSITIVE LOGITS
     ch
    0.89
     Ch
    0.86
    Ch
    0.80
     च
    0.66
     CH
    0.63
     چ
    0.57
     Ч
    0.57
     chl
    0.53
    <0xAE>
    0.52
     chh
    0.51
    Activations Density 0.106%

    No Known Activations