© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214498
    Prev
    Next
    INDEX
    Explanations

    pay-as-you-go

    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
    a
    1.33
    h
    1.29
     a
    1.27
     an
    1.09
     on
    1.05
     as
    1.00
    an
    0.98
    y
    0.96
     was
    0.95
     {
    0.95
    POSITIVE LOGITS
    ών
    0.93
    0.89
    dır
    0.88
    टी
    0.85
     учили
    0.84
    도
    0.82
    تي
    0.81
    િંગ
    0.81
    зме
    0.81
    increases
    0.81
    Activations Density 0.000%

    No Known Activations