© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176800
    Prev
    Next
    INDEX
    Explanations

    licensed clinical professional

    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_20_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
     gratification
    0.51
    வச
    0.46
    returnValue
    0.45
     antich
    0.45
    उनके
    0.44
     Функция
    0.43
     ειδ
    0.42
     อนุ
    0.42
     диапазо
    0.42
    <0x0D>
    0.42
    POSITIVE LOGITS
    la
    0.56
    ela
    0.49
    que
    0.46
    ilo
    0.45
    ihn
    0.45
    lo
    0.45
    categoria
    0.44
    ála
    0.44
    il
    0.44
    ula
    0.43
    Activations Density 0.001%

    No Known Activations