© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49932
    Prev
    Next
    INDEX
    Explanations

    planning aspects

    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_31_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
     chay
    0.42
     созда
    0.39
     Lest
    0.37
    ₁.
    0.37
     Dominic
    0.36
    rosa
    0.35
    ₁,
    0.35
     Cul
    0.34
    apha
    0.34
     ઉત્પ
    0.34
    POSITIVE LOGITS
     refreshments
    0.38
    kW
    0.38
     refreshment
    0.38
    âu
    0.38
    <unused42>
    0.36
     بروز
    0.36
    refresh
    0.36
     kilogram
    0.35
     prevede
    0.35
    ቲክ
    0.35
    Activations Density 0.016%

    No Known Activations