© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13984
    Prev
    Next
    INDEX
    Explanations

    special language constructs

    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_40_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
     Брита
    0.42
     registries
    0.41
    торы
    0.39
     Wren
    0.38
     বিটিআই
    0.38
     registry
    0.37
    Beginning
    0.37
    㝅
    0.37
     тексто
    0.36
     registro
    0.36
    POSITIVE LOGITS
     special
    0.70
     Special
    0.68
    special
    0.66
    Special
    0.66
     specials
    0.60
    スペシャル
    0.59
     specjal
    0.55
     स्पेशल
    0.54
     Specials
    0.54
     SPECIAL
    0.52
    Activations Density 0.000%

    No Known Activations