© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86844
    Prev
    Next
    INDEX
    Explanations

    villainous

    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
    li
    0.73
    z
    0.70
     in
    0.62
     Leveraging
    0.62
    SIZE
    0.59
    tb
    0.59
    りたい
    0.58
    law
    0.56
    ta
    0.56
    size
    0.56
    POSITIVE LOGITS
    ల
    0.78
    ア
    0.76
    ম
    0.75
    આ
    0.70
    ม
    0.68
     abbrevi
    0.67
    த
    0.66
    म
    0.65
    كا
    0.64
    มอง
    0.64
    Activations Density 0.001%

    No Known Activations