© 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. 38881
    Prev
    Next
    INDEX
    Explanations

    party, ambition, search, wants

    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
    ۔
    0.99
    ።
    0.86
    。...
    0.79
    i
    0.75
    。
    0.74
    na
    0.74
    리
    0.72
    mu
    0.71
    duction
    0.71
    Та
    0.71
    POSITIVE LOGITS
    ש
    0.90
    ш
    0.76
    お手
    0.70
    м
    0.69
     Consultez
    0.69
    н
    0.69
    к
    0.68
    ’
    0.67
     Г
    0.65
     wobei
    0.65
    Activations Density 0.071%

    No Known Activations