© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116667
    Prev
    Next
    INDEX
    Explanations

    .yml, audit, Valheim, PrestaShop, rusqlite, amf0, pdfminer, DotNetty, deequ

    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_27_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
     Intern
    0.36
     fellows
    0.34
     interns
    0.34
     Earl
    0.33
     dey
    0.33
    碱
    0.31
     electrolytic
    0.31
     fn
    0.31
     employees
    0.31
     Ira
    0.30
    POSITIVE LOGITS
    prescription
    0.34
    largest
    0.32
     தட
    0.32
    ANZ
    0.30
    放棄
    0.30
    imped
    0.30
     alterar
    0.29
     विशेषता
    0.29
    \{{}\
    0.29
    itada
    0.29
    Activations Density 0.000%

    No Known Activations