© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 48896
    Prev
    Next
    INDEX
    Explanations

    'S' sound

    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_55_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
     літоў
    0.36
    讳
    0.34
    כות
    0.34
     albumen
    0.33
    ComponentModel
    0.32
    нул
    0.32
    énées
    0.32
    မျ
    0.32
    QueryParams
    0.32
     bhfu
    0.32
    POSITIVE LOGITS
    サ
    2.19
     Са
    2.05
    Са
    1.97
    萨
    1.93
     サ
    1.86
     Sá
    1.79
    薩
    1.78
     са
    1.74
     σα
    1.68
     sá
    1.66
    Activations Density 0.033%

    No Known Activations