© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45712
    Prev
    Next
    INDEX
    Explanations

    reduce emissions

    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_22_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
    EXTENSION
    0.26
    CrL
    0.26
     ملعب
    0.26
     PROCEDURE
    0.25
     SPORTS
    0.25
    洌
    0.25
     COVER
    0.25
    醃
    0.25
     chois
    0.25
     ಪ್ರಯತ್ನ
    0.25
    POSITIVE LOGITS
     reducing
    0.26
    ர்களே
    0.25
     pathname
    0.24
     ti
    0.24
    offsetX
    0.24
     strategies
    0.23
     text
    0.23
     dure
    0.23
    fran
    0.23
     जनता
    0.23
    Activations Density 0.082%

    No Known Activations