© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 146295
    Prev
    Next
    INDEX
    Explanations

    LUX, CSA, Towers

    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_0_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
     to
    1.53
    in
    1.52
     and
    1.34
     been
    1.31
     i
    1.29
     de
    1.28
     on
    1.27
     e
    1.17
    ።
    1.13
     l
    1.09
    POSITIVE LOGITS
    t
    2.16
    <0x80>
    1.55
    (
    1.48
    tól
    1.46
    larda
    1.45
    ก
    1.45
    l
    1.34
    ت
    1.34
    lari
    1.32
    ról
    1.28
    Activations Density 0.000%

    No Known Activations