© 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. 36236
    Prev
    Next
    INDEX
    Explanations

    linked list

    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
    y
    0.81
    a
    0.79
    n
    0.72
    b
    0.71
    '
    0.69
    d
    0.69
    ছিলাম
    0.68
    ).
    0.68
    p
    0.65
    ン
    0.64
    POSITIVE LOGITS
     for
    0.80
    for
    0.79
    اري
    0.70
    op
    0.69
    مي
    0.64
     sozial
    0.64
    ip
    0.63
    ру
    0.63
    دين
    0.61
    اريخ
    0.60
    Activations Density 0.001%

    No Known Activations