© 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. 57614
    Prev
    Next
    INDEX
    Explanations

    incorporating

    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
    p
    1.41
    c
    1.34
    ﺭ
    1.34
    TA
    1.32
    ERCISE
    1.28
    dN
    1.26
    H
    1.26
    OVE
    1.24
    K
    1.24
     can
    1.23
    POSITIVE LOGITS
    ات
    1.88
    ة
    1.65
    ون
    1.24
    ъ
    1.23
    ى
    1.22
    ны
    1.20
    ز
    1.18
    ிய
    1.17
    ну
    1.17
    𝐞
    1.17
    Activations Density 0.001%

    No Known Activations