© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106394
    Prev
    Next
    INDEX
    Explanations

    Carbon compounds

    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_1_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
    r
    1.52
    y
    1.37
    t
    1.33
    f
    1.23
    g
    1.21
    s
    1.19
    c
    1.13
    n
    1.13
    l
    1.11
    d
    1.02
    POSITIVE LOGITS
    在
    1.11
     an
    1.02
    的
    1.01
     a
    0.94
    の
    0.93
    เป็น
    0.92
     in
    0.89
    도
    0.88
    จะ
    0.87
    να
    0.86
    Activations Density 0.001%

    No Known Activations