© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 181176
    Prev
    Next
    INDEX
    Explanations

    contract clauses or housing details

    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_24_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
    poc
    0.55
     blackberries
    0.52
    ścic
    0.49
    sü
    0.49
    </code>
    0.47
     wade
    0.46
    `-
    0.46
    сть
    0.46
    instances
    0.45
    Query
    0.44
    POSITIVE LOGITS
    ర్ప
    0.46
     Spearman
    0.44
     cationic
    0.43
     centerline
    0.43
     Dato
    0.42
    抒
    0.42
     berakhir
    0.42
     Haber
    0.41
    <0x8F>
    0.41
     formazione
    0.41
    Activations Density 0.000%

    No Known Activations