© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32048
    Prev
    Next
    INDEX
    Explanations

    supervised learning algorithms

    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_40_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
     зада
    0.38
     tla
    0.37
     फड
    0.37
    官
    0.36
     llen
    0.35
     ثابت
    0.35
     anticipate
    0.34
     inform
    0.33
     governmental
    0.33
     anticipation
    0.33
    POSITIVE LOGITS
     Linear
    0.42
     supervised
    0.38
    Linear
    0.37
     Accuracy
    0.36
    Map
    0.36
    supervised
    0.36
    linear
    0.36
    \|\
    0.35
    баты
    0.35
    Naive
    0.35
    Activations Density 0.018%

    No Known Activations