© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 218420
    Prev
    Next
    INDEX
    Explanations

    shown

    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_47_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
     mäng
    0.41
     mindestens
    0.38
     பாவ
    0.38
     массив
    0.37
    愼
    0.37
     бер
    0.37
     француз
    0.37
     savaş
    0.36
    ：%
    0.36
    :%
    0.36
    POSITIVE LOGITS
    led
    0.39
    cha
    0.39
    χαν
    0.39
    arlı
    0.39
    clar
    0.36
    far
    0.36
     far
    0.36
    ianos
    0.36
    ches
    0.36
    जे
    0.35
    Activations Density 0.001%

    No Known Activations