© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 85758
    Prev
    Next
    INDEX
    Explanations

    article "an"

    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_18_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
    jected
    0.46
     pinching
    0.45
    િંગ
    0.45
    കെ
    0.45
    as
    0.42
    다
    0.42
    stituting
    0.42
    ിക
    0.41
     crossed
    0.41
    Celebrate
    0.41
    POSITIVE LOGITS
     Н
    0.57
    <0x0D>
    0.50
    рактери
    0.48
     entero
    0.47
    зно
    0.47
    ()->
    0.47
    ИН
    0.46
    otry
    0.46
    osto
    0.46
     н
    0.46
    Activations Density 0.007%

    No Known Activations