© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130190
    Prev
    Next
    INDEX
    Explanations

    cashier

    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_1_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
    ک
    1.41
    ט
    1.34
    ル
    1.34
    ل
    1.32
    л
    1.31
    ल
    1.30
    ก
    1.30
    t
    1.27
    си
    1.23
    ク
    1.21
    POSITIVE LOGITS
    :
    1.33
    .
    1.22
     in
    1.15
     to
    1.11
    ing
    1.09
    ation
    1.09
     are
    1.06
     y
    1.03
    ight
    1.01
     mache
    1.01
    Activations Density 0.000%

    No Known Activations