© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62942
    Prev
    Next
    INDEX
    Explanations

    Thielaviopsis Paradoxa / Thiele/Small

    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_2_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
    O
    1.47
    E
    1.24
    {
    1.23
    U
    1.23
    О
    1.20
    ع
    1.19
    B
    1.17
    }$.
    1.16
    ك
    1.14
    }$
    1.12
    POSITIVE LOGITS
     (
    1.15
     on
    0.97
     VIII
    0.75
     Москвы
    0.72
    dominal
    0.71
    iong
    0.70
     Архивная
    0.70
     are
    0.68
     It
    0.68
     महासभा
    0.67
    Activations Density 0.002%

    No Known Activations