© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53114
    Prev
    Next
    INDEX
    Explanations

    closing braces or parentheses

    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_31_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
    Ost
    0.36
    Schw
    0.36
    Monday
    0.34
    Require
    0.34
    Boston
    0.33
    }-{
    0.33
    (-
    0.32
    Cold
    0.31
     ~/
    0.31
    omus
    0.31
    POSITIVE LOGITS
     заниматься
    0.38
    빌
    0.37
    outch
    0.37
     작품
    0.37
     acción
    0.35
     mezcla
    0.35
     सांगतात
    0.35
    стів
    0.35
     짜
    0.35
    hookrightarrow
    0.34
    Activations Density 0.006%

    No Known Activations