© 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. 8961
    Prev
    Next
    INDEX
    Explanations

    to + verb

    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
    Residual
    0.31
     fue
    0.30
    Nag
    0.30
    Recovery
    0.29
    Sal
    0.29
    Endpoint
    0.29
    [
    0.28
    Vac
    0.28
    でした
    0.28
    פ
    0.27
    POSITIVE LOGITS
    r
    0.36
    скага
    0.35
    ంచు
    0.32
    utico
    0.31
     produzido
    0.31
    <0xA1>
    0.31
     јуну
    0.31
    𝖊
    0.30
    nex
    0.30
    abá
    0.30
    Activations Density 0.045%

    No Known Activations