© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31734
    Prev
    Next
    INDEX
    Explanations

    say "wh" words

    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
    nio
    0.41
    ября
    0.39
    pio
    0.39
    дается
    0.39
    бир
    0.36
    𐰤
    0.36
     epis
    0.35
     خر
    0.35
    Ⲇ
    0.35
    ტო
    0.34
    POSITIVE LOGITS
     wh
    2.75
     Wh
    2.59
    wh
    2.45
    Wh
    2.44
     WH
    1.82
    WH
    1.77
     whi
    1.54
     whack
    1.34
     whaling
    1.30
     w
    1.18
    Activations Density 0.007%

    No Known Activations