© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 146936
    Prev
    Next
    INDEX
    Explanations

    six

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    vii
    0.42
    '-
    0.41
    VII
    0.40
     ≠
    0.40
     VII
    0.39
    #-
    0.38
    rx
    0.38
    iacute
    0.38
     vii
    0.38
    .#
    0.37
    POSITIVE LOGITS
    6
    1.86
    ６
    1.61
    ۶
    1.45
     six
    1.41
     ۶
    1.41
     ৬
    1.36
     Six
    1.33
    六
    1.33
     ६
    1.31
    ৬
    1.31
    Activations Density 0.005%

    No Known Activations