© 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. 206598
    Prev
    Next
    INDEX
    Explanations

    request, response, object, content

    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
     chips
    0.86
    在
    0.84
     in
    0.80
     chip
    0.80
    لر
    0.75
    <
    0.74
     lingua
    0.73
     gomme
    0.73
     were
    0.72
     este
    0.72
    POSITIVE LOGITS
    </strong>
    0.73
    ittel
    0.71
    agas
    0.69
    assment
    0.68
    antum
    0.64
    aithe
    0.64
    pan
    0.62
    ulp
    0.61
    inces
    0.61
    ompok
    0.61
    Activations Density 0.002%

    No Known Activations