© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26564
    Prev
    Next
    INDEX
    Explanations

    prognosis and outcomes

    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_10_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
    am
    0.66
    ał
    0.65
    don
    0.64
    dut
    0.64
    i
    0.63
    d
    0.62
    a
    0.61
    n
    0.61
    Ằ
    0.61
    dba
    0.61
    POSITIVE LOGITS
    и
    0.65
    이었다
    0.57
    을
    0.56
    ність
    0.56
    发起
    0.54
    지고
    0.53
    虎
    0.51
    感じで
    0.50
     residencial
    0.50
    してみ
    0.50
    Activations Density 0.017%

    No Known Activations