© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6111
    Prev
    Next
    INDEX
    Explanations

    python code

    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_39_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
    十六
    0.35
     स्नात
    0.34
    நட
    0.33
    ʦ
    0.31
    *((*
    0.31
     keyDown
    0.31
    ივ
    0.31
     loko
    0.30
     લો
    0.29
     mish
    0.29
    POSITIVE LOGITS
     cognitive
    0.32
    cognitive
    0.32
    ellige
    0.31
    新型
    0.31
    ...]
    0.31
    rosine
    0.30
    最好的
    0.30
     Armed
    0.29
    讠
    0.29
     Defense
    0.29
    Activations Density 0.020%

    No Known Activations