© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 194382
    Prev
    Next
    INDEX
    Explanations

    CTC (closed time-like curves)

    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_9_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
    c
    1.13
    }`
    0.85
    $,
    0.85
    、
    0.84
    ，
    0.83
    ：
    0.83
    new
    0.82
    r
    0.80
    }")
    0.78
    type
    0.76
    POSITIVE LOGITS
    م
    1.47
    м
    1.15
    ம்
    1.13
    ला
    1.09
    ন
    1.09
     phospholipids
    0.98
     marinas
    0.95
     stereotypes
    0.94
     beetles
    0.93
     convolutions
    0.93
    Activations Density 0.000%

    No Known Activations