© 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. 45653
    Prev
    Next
    INDEX
    Explanations

    Brian Eno

    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
    sstream
    0.14
    тво
    0.13
    ィ
    0.13
     أبو
    0.12
     أبي
    0.12
     eloquently
    0.12
     willing
    0.12
    خ
    0.11
    сера
    0.11
     ப
    0.11
    POSITIVE LOGITS
     cesta
    0.13
    <unused28>
    0.12
     sitä
    0.12
    leans
    0.12
     används
    0.12
     bombshell
    0.12
    नाची
    0.12
     Creole
    0.12
     keselamatan
    0.12
     kasv
    0.12
    Activations Density 0.002%

    No Known Activations