© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17733
    Prev
    Next
    INDEX
    Explanations

    increase or decrease by percentage

    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_34_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
    பன்
    0.36
     ping
    0.35
     限
    0.35
     frust
    0.34
    partials
    0.34
     frustration
    0.34
    ვის
    0.33
     qīng
    0.33
     hai
    0.32
     adicional
    0.32
    POSITIVE LOGITS
     Decrease
    0.58
     শতকরা
    0.57
     decrease
    0.55
     decreased
    0.54
    decrease
    0.52
    Decrease
    0.52
     (+
    0.52
    increase
    0.51
     increase
    0.50
     aumentó
    0.50
    Activations Density 0.025%

    No Known Activations