© 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. 122503
    Prev
    Next
    INDEX
    Explanations

    savoy, sabzi, sabino

    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
    K
    0.91
    _
    0.72
    N
    0.71
    wirkung
    0.70
    I
    0.68
    Go
    0.66
     It
    0.65
    Y
    0.65
    的大
    0.64
    arak
    0.64
    POSITIVE LOGITS
    nip
    0.89
    n
    0.86
    ला
    0.86
    та
    0.83
    ή
    0.83
    ת
    0.83
    т
    0.82
    ができる
    0.80
     tẩy
    0.80
    не
    0.80
    Activations Density 0.000%

    No Known Activations