© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58120
    Prev
    Next
    INDEX
    Explanations

    size and layout

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    எம்
    0.44
    എം
    0.43
    bx
    0.42
    brix
    0.42
    Ｍ
    0.41
     എം
    0.40
    o
    0.40
    एम
    0.40
     एम
    0.40
    𝑀
    0.40
    POSITIVE LOGITS
     ring
    0.65
     Ring
    0.58
    ↵
    0.57
     -
    0.54
     RING
    0.52
    环
    0.50
     dark
    0.50
     group
    0.48
    Ring
    0.47
    ";
    0.46
    Activations Density 0.003%

    No Known Activations