© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50039
    Prev
    Next
    INDEX
    Explanations

    press releases and articles

    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_10_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
     Ukraj
    0.41
    ä
    0.39
    ne
    0.39
    Ğ
    0.39
     roky
    0.38
    ę
    0.38
     。
    0.37
    Ę
    0.37
    ም።
    0.37
     Međ
    0.36
    POSITIVE LOGITS
    a
    0.38
    (
    0.36
    beams
    0.32
     pyramid
    0.30
    ’
    0.30
    at
    0.28
    澄
    0.28
    as
    0.28
     pyramidal
    0.28
    ier
    0.28
    Activations Density 0.030%

    No Known Activations