© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 148509
    Prev
    Next
    INDEX
    Explanations

    wa/va 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_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
     لنا
    0.53
     «
    0.50
    «
    0.46
     পেয়েছে
    0.44
    Na
    0.43
     Na
    0.43
    «,
    0.42
     na
    0.40
     одной
    0.40
     Боль
    0.39
    POSITIVE LOGITS
     wa
    0.70
     Wa
    0.64
    約
    0.64
     Va
    0.62
     ва
    0.59
     約
    0.57
     về
    0.57
     va
    0.56
    Va
    0.55
     वा
    0.54
    Activations Density 0.002%

    No Known Activations