© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 205354
    Prev
    Next
    INDEX
    Explanations

    these characters / sounds / companies / objects

    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
    Negative Logits
    <
    0.50
    _
    0.49
    ’,
    0.46
    <h4>
    0.46
    2
    0.44
    acht
    0.44
     مث
    0.42
    RI
    0.40
    </body>
    0.40
    sz
    0.39
    POSITIVE LOGITS
    el
    0.51
    ed
    0.50
     一个
    0.49
    ด
    0.48
    ફળ
    0.47
     bullpen
    0.47
     bộ
    0.47
    У
    0.47
     científico
    0.46
     tòa
    0.46
    Activations Density 0.005%

    No Known Activations