© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44875
    Prev
    Next
    INDEX
    Explanations

    You Need A Budget

    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_3_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
    يل
    0.79
    0
    0.73
    in
    0.67
     партия
    0.65
    erin
    0.64
    inį
    0.62
     of
    0.62
    ០
    0.62
    ານ
    0.61
     Süden
    0.61
    POSITIVE LOGITS
    ן
    0.87
    ку
    0.68
    ד
    0.66
     facsimile
    0.66
    闓
    0.63
    nahme
    0.63
    ס
    0.61
     cuya
    0.60
     makeshift
    0.60
    aisu
    0.60
    Activations Density 0.003%

    No Known Activations