© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176414
    Prev
    Next
    INDEX
    Explanations

    permissions

    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_20_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
     ಅವರನ್ನು
    0.43
    comes
    0.42
    ၷ
    0.41
    those
    0.41
    delayed
    0.41
    obacterial
    0.40
    ोसी
    0.39
     ಅನುಪ
    0.39
     પ્રતિબિં
    0.39
    ermi
    0.39
    POSITIVE LOGITS
     Sly
    0.46
     Uso
    0.46
     vers
    0.46
     code
    0.46
     förs
    0.46
     tags
    0.45
     (
    0.45
     θέ
    0.45
     IC
    0.43
     themes
    0.43
    Activations Density 0.001%

    No Known Activations