© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 102967
    Prev
    Next
    INDEX
    Explanations

    insider knowledge

    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_1_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
    ون
    1.45
    و
    1.44
    다
    1.38
    ა
    1.37
    ed
    1.34
    ات
    1.26
    ม
    1.26
    ک
    1.23
    es
    1.16
    ด
    1.16
    POSITIVE LOGITS
    :
    1.37
     mastect
    1.24
     absolv
    1.15
     analiz
    1.13
     exclu
    1.11
     skladu
    1.09
     desliz
    1.07
    𝔹
    1.05
     acerc
    1.04
     acredit
    1.02
    Activations Density 0.002%

    No Known Activations