© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107328
    Prev
    Next
    INDEX
    Explanations

    ella

    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
    (
    1.30
    ก
    1.27
    ED
    1.24
    <0x0D>
    1.09
    Для
    1.09
     has
    1.08
     WITH
    1.08
    </strong>
    1.06
    OD
    1.06
    のための
    1.05
    POSITIVE LOGITS
    in
    1.26
    for
    0.94
    end
    0.91
    oc
    0.90
    iş
    0.89
    o
    0.89
    collation
    0.88
    ைட்
    0.86
     بچے
    0.86
    ung
    0.85
    Activations Density 0.000%

    No Known Activations