© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 261009
    Prev
    Next
    INDEX
    Explanations

    external validity

    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_22_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
     بیماری
    0.49
    嫔
    0.47
     malattia
    0.42
     maladie
    0.42
     misdeme
    0.40
     antérieur
    0.39
     malattie
    0.39
     prioritise
    0.39
    াহ্ম
    0.38
     Earle
    0.38
    POSITIVE LOGITS
     кры
    0.45
    czak
    0.42
     +
    0.41
    rades
    0.41
     Plantation
    0.40
     zlat
    0.40
    íts
    0.40
     Zig
    0.40
     ഭാഗ
    0.40
    urais
    0.40
    Activations Density 0.000%

    No Known Activations