© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44037
    Prev
    Next
    INDEX
    Explanations

    seeking what is desired

    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_13_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
    en
    0.71
    an
    0.63
    (
    0.60
    Get
    0.54
    at
    0.53
    on
    0.51
    ee
    0.51
    us
    0.51
    Track
    0.49
    canoe
    0.49
    POSITIVE LOGITS
    ｐ
    0.51
     estimating
    0.50
    ాల్లో
    0.50
    定量
    0.50
    的身
    0.49
     متنوع
    0.49
    绚
    0.49
     రూపాయ
    0.49
     surpluses
    0.49
     રૂપિયા
    0.48
    Activations Density 0.012%

    No Known Activations