© 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. 84056
    Prev
    Next
    INDEX
    Explanations

    switches, glitches, ditches

    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
    <0x80>
    1.21
    ни
    1.09
    that
    1.09
    но
    1.08
    м
    1.01
    <0xA0>
    1.00
    ть
    0.99
    '
    0.99
    䢎
    0.98
    ι
    0.95
    POSITIVE LOGITS
     in
    2.66
     are
    2.22
     at
    1.82
     be
    1.48
     on
    1.41
     for
    1.34
     as
    1.30
    ।
    1.27
     is
    1.23
     not
    1.23
    Activations Density 0.000%

    No Known Activations