© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202212
    Prev
    Next
    INDEX
    Explanations

    cro(ssants, pping, chet, atia)

    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_6_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
    -
    0.87
    '
    0.84
    {
    0.76
    ння
    0.74
    (
    0.73
    ull
    0.71
     are
    0.68
     be
    0.66
    ﭼ
    0.65
    ି
    0.65
    POSITIVE LOGITS
    im
    1.40
    ak
    1.25
    on
    1.20
    ب
    1.16
    is
    1.10
    am
    1.09
    न
    1.09
    م
    1.07
    and
    1.05
    un
    1.03
    Activations Density 0.001%

    No Known Activations