© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62535
    Prev
    Next
    INDEX
    Explanations

    describing an excerpt

    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_11_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
    ።
    0.64
     हालाँकि
    0.54
     killing
    0.53
     නමුත්
    0.50
    سكر
    0.50
     Bits
    0.50
     मिनिस्टर
    0.50
     While
    0.49
     clueless
    0.49
     genauso
    0.49
    POSITIVE LOGITS
    1
    0.69
    ू
    0.65
    an
    0.64
    ون
    0.63
    ses
    0.63
    6
    0.61
    িয়া
    0.61
    ların
    0.60
     seis
    0.60
    f
    0.60
    Activations Density 0.001%

    No Known Activations