© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 47841
    Prev
    Next
    INDEX
    Explanations

    code docstrings

    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_10_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
     can
    1.02
    ä
    1.02
    ки
    0.99
    зи
    0.89
    can
    0.88
    ag
    0.87
    <0xA4>
    0.85
    п
    0.83
    ай
    0.81
    '
    0.79
    POSITIVE LOGITS
    ו
    1.05
    jene
    0.84
    gget
    0.81
    u
    0.79
     ReturnVal
    0.78
    verständlich
    0.76
    icient
    0.71
    ק
    0.70
    jelen
    0.68
    "}
    0.66
    Activations Density 0.001%

    No Known Activations