© 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. 125110
    Prev
    Next
    INDEX
    Explanations

    WIP gene

    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
    琯
    0.39
    sak
    0.38
    Cycling
    0.37
    }{|
    0.35
     石
    0.35
    ড্ডা
    0.35
    duplicated
    0.34
    stone
    0.34
     Cycling
    0.34
    ској
    0.34
    POSITIVE LOGITS
    arios
    0.40
    ismos
    0.39
     interrupt
    0.37
     ਤੁ
    0.36
     inten
    0.36
    PERIOD
    0.35
     PBL
    0.35
    Anyways
    0.35
     période
    0.34
    난
    0.34
    Activations Density 0.000%

    No Known Activations