© 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. 133159
    Prev
    Next
    INDEX
    Explanations

    A followed by period or word

    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
    า
    1.61
     are
    1.59
    ad
    1.30
    ла
    1.20
    ל
    1.20
    то
    1.18
     at
    1.16
    б
    1.14
    на
    1.09
    <0x0D>
    1.08
    POSITIVE LOGITS
    İ
    1.40
    in
    1.34
    Y
    1.27
    Gö
    1.27
    G
    1.26
    C
    1.25
    d
    1.20
    K
    1.14
    Dü
    1.12
     in
    1.11
    Activations Density 0.000%

    No Known Activations