© 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. 213514
    Prev
    Next
    INDEX
    Explanations

    nanometers

    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
     as
    1.88
     at
    1.69
     are
    1.63
     in
    1.56
    า
    1.52
    '
    1.43
    да
    1.41
     a
    1.27
    리
    1.22
    f
    1.20
    POSITIVE LOGITS
    with
    1.33
    ments
    1.23
    一
    1.19
    ל
    1.14
    C
    1.09
    ap
    1.05
    uant
    1.02
    بد
    1.01
    ς
    0.99
    the
    0.99
    Activations Density 0.002%

    No Known Activations