© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 222064
    Prev
    Next
    INDEX
    Explanations

    yaml files

    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_10_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
    s
    0.29
    ;
    0.27
    ances
    0.26
    지
    0.26
    σε
    0.26
    <h2>
    0.25
    ش
    0.25
    ch
    0.25
    d
    0.25
     jim
    0.24
    POSITIVE LOGITS
    tų
    0.30
    ون
    0.28
    transfected
    0.28
     stipulates
    0.27
     Uttarakhand
    0.27
    tare
    0.26
    Constitution
    0.26
    ۸
    0.26
     Конститу
    0.26
    planetary
    0.25
    Activations Density 0.004%

    No Known Activations