© 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. 147247
    Prev
    Next
    INDEX
    Explanations

    0

    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
     આન
    0.37
    uyeron
    0.37
    ຶ
    0.37
    𝓻
    0.36
     **
    0.36
     []),
    0.36
     있으
    0.35
     `<=`
    0.35
    eritud
    0.35
    yatiti
    0.35
    POSITIVE LOGITS
    8
    0.68
     VIII
    0.64
     eighty
    0.56
     Eighth
    0.56
    ۸
    0.54
    VIII
    0.53
    ８
    0.53
    7
    0.52
    -
    0.52
     eight
    0.52
    Activations Density 0.000%

    No Known Activations