© 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. 197265
    Prev
    Next
    INDEX
    Explanations

    brand names

    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
    Rite
    0.35
    caire
    0.35
    vertine
    0.35
    Puede
    0.34
     pariy
    0.34
     राखी
    0.33
    ன்மையான
    0.33
     ;-
    0.33
    трі
    0.33
    トリック
    0.33
    POSITIVE LOGITS
     ગા
    0.35
     mathcolor
    0.33
    colorControl
    0.33
    赋予
    0.33
     कू
    0.32
    Xu
    0.32
    ANOVA
    0.32
     cxd
    0.32
     સૂ
    0.30
     اجازه
    0.30
    Activations Density 0.000%

    No Known Activations