© 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. 45971
    Prev
    Next
    INDEX
    Explanations

    amount of

    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
    다
    0.83
    ಸ್
    0.75
    า
    0.72
    ۵
    0.72
    한
    0.70
    수
    0.69
    心の
    0.67
    ۶
    0.66
    おすすめ
    0.65
    də
    0.64
    POSITIVE LOGITS
    ني
    0.67
     lanz
    0.67
    nder
    0.61
     separ
    0.61
    ne
    0.59
    or
    0.58
    je
    0.58
    m
    0.57
    ag
    0.56
    ri
    0.56
    Activations Density 0.002%

    No Known Activations