© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 131030
    Prev
    Next
    INDEX
    Explanations

    request to please do not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
     ব্যর্থ
    0.39
    ные
    0.37
     bonding
    0.37
    대를
    0.37
     Bonding
    0.37
    тические
    0.36
    
    0.36
     LINES
    0.35
     Những
    0.35
    тических
    0.35
    POSITIVE LOGITS
     decreed
    0.42
     trou
    0.39
    ല്
    0.38
     know
    0.38
     decreto
    0.38
     figurine
    0.38
     eternally
    0.38
    磬
    0.37
     caza
    0.37
    prev
    0.36
    Activations Density 0.000%

    No Known Activations