© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 206218
    Prev
    Next
    INDEX
    Explanations

    say "-ings" ending

    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_56_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
    嘣
    0.37
    itsi
    0.36
    ၷ
    0.34
     entram
    0.34
     bracelet
    0.33
    堵
    0.33
    <unused2213>
    0.33
     अटेम्प्ट
    0.33
    旗
    0.33
    ိပ်
    0.32
    POSITIVE LOGITS
     mus
    2.42
     Mus
    1.95
    Mus
    1.95
    mus
    1.84
     MUS
    1.45
    MUS
    1.38
     ramb
    1.23
     musk
    1.11
     rav
    1.07
    ings
    1.02
    Activations Density 0.002%

    No Known Activations