© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 134183
    Prev
    Next
    INDEX
    Explanations

    cable

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    W
    0.51
     W
    0.46
    Ｗ
    0.46
    STRU
    0.42
     unrealistic
    0.41
    Archer
    0.41
     Mc
    0.39
    FD
    0.39
    标
    0.39
    akul
    0.39
    POSITIVE LOGITS
    Cable
    0.47
     Cable
    0.44
     cable
    0.43
     कबड्डी
    0.43
     Cables
    0.41
     Pantone
    0.40
    cable
    0.39
     Elizabeth
    0.39
     tangente
    0.39
    Elizabeth
    0.38
    Activations Density 0.021%

    No Known Activations