© 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. 202733
    Prev
    Next
    INDEX
    Explanations

    screw head types

    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
     g
    0.53
     travail
    0.47
    шого
    0.46
         
    0.46
    ated
    0.45
     clav
    0.45
    g
    0.45
    bs
    0.44
     screws
    0.44
     tous
    0.44
    POSITIVE LOGITS
     inactivació
    0.48
    
    0.48
     yolks
    0.46
    ダイニング
    0.46
     deplete
    0.45
    IdleSync
    0.45
     உங்களுக்கு
    0.45
     வண்ணப்பூ
    0.44
    Westinghouse
    0.44
    𒋼
    0.44
    Activations Density 0.007%

    No Known Activations