© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62803
    Prev
    Next
    INDEX
    Explanations

    say "holes"

    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_59_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
     holes
    1.27
     Holes
    1.13
    holes
    1.05
     trous
    0.91
     hole
    0.80
    hole
    0.79
     Hole
    0.70
    穴
    0.70
     aguj
    0.64
     отверсти
    0.64
    POSITIVE LOGITS
     wholes
    0.49
     ஓ
    0.48
    洞
    0.44
     пост
    0.41
     wishes
    0.39
     deserves
    0.39
     vent
    0.38
     drain
    0.38
     post
    0.37
     كون
    0.37
    Activations Density 0.009%

    No Known Activations