© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136765
    Prev
    Next
    INDEX
    Explanations

    Jupyter Notebook

    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_12_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
     Cancell
    0.46
    섯
    0.44
    লা
    0.44
    Dedicated
    0.44
     Dedicated
    0.43
     videomuz
    0.43
    անակ
    0.43
    იმ
    0.42
    getUserMedia
    0.42
     sess
    0.42
    POSITIVE LOGITS
    t
    0.46
     Thames
    0.43
     могли
    0.42
    jaar
    0.42
     таке
    0.41
    it
    0.41
    '
    0.41
    𝑢
    0.40
     İng
    0.40
     ситуацию
    0.40
    Activations Density 0.004%

    No Known Activations