© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108015
    Prev
    Next
    INDEX
    Explanations

    Shayna, Woods, Shaytan

    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
    Not in Any Lists

    No Comments

    Negative Logits
    {
    1.56
    した
    1.44
    0
    1.42
    。
    1.41
    ۰
    1.30
     of
    1.25
    ።
    1.20
     are
    1.18
    انی
    1.17
     be
    1.15
    POSITIVE LOGITS
    s
    1.47
    es
    1.45
    as
    1.44
    n
    1.38
    os
    1.32
    it
    1.30
    an
    1.27
    ar
    1.20
    d
    1.19
    a
    1.18
    Activations Density 0.000%

    No Known Activations