© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13869
    Prev
    Next
    INDEX
    Explanations

    posits or proposes theories

    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_13_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
    готовка
    0.28
     декора
    0.28
     Decay
    0.28
     Jacoby
    0.27
    巨大
    0.27
    <unused593>
    0.27
     କରି
    0.27
     anomalous
    0.26
    satz
    0.26
    finaly
    0.26
    POSITIVE LOGITS
    [
    0.31
    자
    0.27
    ća
    0.27
     scheme
    0.26
     IS
    0.26
     शाळा
    0.26
    Hãy
    0.26
     offer
    0.26
    お
    0.25
     passag
    0.25
    Activations Density 0.213%

    No Known Activations