© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124905
    Prev
    Next
    INDEX
    Explanations

    paperless billing or post

    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_3_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
    3
    0.86
    4
    0.80
    1
    0.77
    ت
    0.75
    تان
    0.71
    6
    0.70
    ாடி
    0.66
    ແມ
    0.65
     क्रमा
    0.65
    5
    0.65
    POSITIVE LOGITS
     be
    0.74
    Paper
    0.70
    '
    0.68
    వ
    0.66
    ü
    0.61
     unbe
    0.58
    TIME
    0.58
    be
    0.56
    而
    0.56
    বি
    0.55
    Activations Density 0.001%

    No Known Activations