© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 197932
    Prev
    Next
    INDEX
    Explanations

    starting or taking action

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Fauci
    0.38
    宴
    0.36
     된
    0.35
    ندق
    0.34
     recess
    0.33
    崙
    0.33
     up
    0.33
     aw
    0.33
    credit
    0.32
     Cornell
    0.32
    POSITIVE LOGITS
    AMINATION
    0.39
    รือ
    0.38
     ಕೇಳ
    0.38
    пер
    0.37
     देखकर
    0.37
    igur
    0.37
    QRCode
    0.36
    ByteBuffer
    0.36
     informée
    0.36
     الاست
    0.35
    Activations Density 0.001%

    No Known Activations