© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 228610
    Prev
    Next
    INDEX
    Explanations

    sal followed by 'utation', 'acious', or 'oon'

    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_6_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
    DA
    0.96
    라
    0.84
    VING
    0.83
    र
    0.83
    CP
    0.82
    아
    0.82
    ม
    0.79
    BackgroundHelper
    0.79
    า
    0.76
    DP
    0.74
    POSITIVE LOGITS
    an
    0.86
    h
    0.80
    ان
    0.76
    v
    0.75
    ι
    0.70
    اری
    0.70
    ваме
    0.68
    ва
    0.68
    υ
    0.67
    и
    0.66
    Activations Density 0.001%

    No Known Activations