© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45960
    Prev
    Next
    INDEX
    Explanations

    inner lining

    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_13_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
    芓
    0.59
    㫣
    0.59
     लंबा
    0.57
    雬
    0.57
     `>=`,
    0.57
    '`--'`--
    0.55
    氀
    0.55
     broaden
    0.55
     outperform
    0.54
     defraud
    0.54
    POSITIVE LOGITS
    م
    0.63
    man
    0.55
     service
    0.54
    service
    0.54
    air
    0.54
    </strong>
    0.53
     (
    0.53
    Man
    0.51
    net
    0.50
    נת
    0.50
    Activations Density 0.001%

    No Known Activations