© 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. 146097
    Prev
    Next
    INDEX
    Explanations

    say https

    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
     ``
    0.56
     ‘‘
    0.51
     ‘’
    0.48
    ‘‘
    0.48
     ‌
    0.47
    "
    0.46
     ″
    0.46
     ‏
    0.45
    〝
    0.44
     !",
    0.44
    POSITIVE LOGITS
    надца
    0.40
    dan
    0.38
    Packages
    0.38
    da
    0.37
    anda
    0.37
    eller
    0.36
    瘓
    0.36
    piperidin
    0.36
    </thead>
    0.36
    नावश्यक
    0.36
    Activations Density 0.000%

    No Known Activations