© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159885
    Prev
    Next
    INDEX
    Explanations

    cosmopolitan or cosmological

    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_2_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
     insect
    1.06
    ง่าย
    1.00
     ailing
    0.98
    ום
    0.98
    צ
    0.97
     cranks
    0.95
    )\}
    0.95
     ailment
    0.94
    די
    0.93
     economist
    0.92
    POSITIVE LOGITS
    t
    2.23
    m
    1.98
    h
    1.91
    an
    1.65
    i
    1.64
    y
    1.51
    p
    1.50
    un
    1.49
    s
    1.43
    u
    1.42
    Activations Density 0.000%

    No Known Activations