© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 215367
    Prev
    Next
    INDEX
    Explanations

    advanced math/science

    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
     reflex
    0.40
     deck
    0.40
     ರ
    0.39
    Deck
    0.38
     Siz
    0.38
     رائے
    0.38
     RES
    0.37
     Deck
    0.37
    deck
    0.36
    uZ
    0.36
    POSITIVE LOGITS
    玻
    0.40
    rowave
    0.37
     கத
    0.37
     weep
    0.36
    ั่ว
    0.35
    íb
    0.35
     колон
    0.35
    enson
    0.34
    镀
    0.34
     बता
    0.34
    Activations Density 0.000%

    No Known Activations