© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91906
    Prev
    Next
    INDEX
    Explanations

    curva de aprendizaje

    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_11_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
    Õ
    0.63
     introduce
    0.54
     encompass
    0.53
     chronically
    0.53
     not
    0.53
     alphabetically
    0.53
     your
    0.52
     wprowad
    0.52
     trained
    0.52
     besch
    0.52
    POSITIVE LOGITS
    reset
    0.54
     முயற்சி
    0.53
    ਾਰ
    0.51
    ствием
    0.51
    𝕡
    0.50
    ällä
    0.48
    𝕠
    0.48
    𝕣
    0.48
    료
    0.47
     کنند
    0.47
    Activations Density 0.001%

    No Known Activations