© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 142355
    Prev
    Next
    INDEX
    Explanations

    matrix representations of basis

    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_12_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
    province
    0.58
    ";
    0.56
    left
    0.55
    ProductID
    0.55
    Province
    0.54
    linen
    0.54
    विज्ञापन
    0.53
    detected
    0.53
    Oste
    0.53
    1
    0.52
    POSITIVE LOGITS
     grud
    0.60
     Sadler
    0.52
     mirar
    0.52
     incred
    0.52
     apro
    0.52
    บูร
    0.52
     Aten
    0.50
     atlet
    0.50
     aggi
    0.50
     vor
    0.48
    Activations Density 0.000%

    No Known Activations