© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211355
    Prev
    Next
    INDEX
    Explanations

    forming a/the

    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_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    o
    1.32
    ?
    1.17
    럏
    1.12
     entidades
    1.11
     comenc
    1.09
    ()
    1.08
     sigu
    1.07
    _
    1.06
    اليه
    1.05
    \*
    1.04
    POSITIVE LOGITS
     (
    1.65
     .
    1.34
    na
    1.32
     in
    1.31
     to
    1.27
    at
    1.20
    ка
    1.15
    arı
    1.04
     в
    1.03
    ma
    1.01
    Activations Density 0.001%

    No Known Activations