© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 138815
    Prev
    Next
    INDEX
    Explanations

    line

    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_37_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
    છી
    0.36
     regalos
    0.35
    到了
    0.35
     শব্দ
    0.35
     Sib
    0.34
    [-]
    0.34
    瑷
    0.34
    চারের
    0.33
    [{
    0.33
    amnt
    0.33
    POSITIVE LOGITS
    Assuming
    0.36
     norepinephrine
    0.36
     сухо
    0.34
    けて
    0.34
     teles
    0.34
     επο
    0.34
    Insufficient
    0.34
    保
    0.34
    ertime
    0.33
     सूखा
    0.33
    Activations Density 0.003%

    No Known Activations