© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 90075
    Prev
    Next
    INDEX
    Explanations

    quotes

    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_60_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
    <em>
    0.97
    <strong>
    0.71
     *
    0.66
     \*
    0.59
     $*$
    0.59
    </strong>
    0.57
     $-$
    0.57
     —
    0.55
    </em>
    0.54
     -
    0.54
    POSITIVE LOGITS
    new
    0.57
    After
    0.56
    These
    0.55
    ใหม่
    0.53
    নতুন
    0.52
    ‘
    0.50
    新しい
    0.50
    新たな
    0.50
    It
    0.47
     nuova
    0.46
    Activations Density 0.000%

    No Known Activations