© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 204633
    Prev
    Next
    INDEX
    Explanations

    calculator code

    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
    candy
    0.40
    eeper
    0.38
     candy
    0.37
     Supplies
    0.36
    タッチ
    0.35
    🅔
    0.35
    underwear
    0.35
    assel
    0.35
    ỵ
    0.35
    ুলি
    0.34
    POSITIVE LOGITS
     Anglic
    0.38
     sib
    0.37
    једина
    0.37
     ros
    0.36
     ينا
    0.36
     gestalt
    0.36
    ubon
    0.35
     mart
    0.35
    acariy
    0.35
     Ley
    0.34
    Activations Density 0.004%

    No Known Activations