© 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. 239101
    Prev
    Next
    INDEX
    Explanations

    link tags and attributes

    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
     (>
    0.39
    ẵn
    0.36
     উপস্থিত
    0.35
     '>
    0.34
     (<
    0.34
    ាំ
    0.33
     被
    0.33
    |^
    0.33
    被
    0.33
    有
    0.32
    POSITIVE LOGITS
    >]</
    0.46
     administrativa
    0.43
     துவ
    0.42
    тата
    0.42
     revi
    0.42
    लेकिन
    0.41
     administratif
    0.41
     administrativos
    0.41
     han
    0.40
    अब
    0.40
    Activations Density 0.000%

    No Known Activations