© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 206156
    Prev
    Next
    INDEX
    Explanations

    cosmic rays and energy particles

    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
    <0x0D>
    0.62
    ur
    0.62
    at
    0.60
    یم
    0.60
    ra
    0.59
    ts
    0.59
    ut
    0.59
    0
    0.59
    ’
    0.59
    ’),
    0.58
    POSITIVE LOGITS
     dvě
    0.49
     două
    0.48
    电视台
    0.45
    Sampling
    0.45
     be
    0.44
     zwei
    0.44
    ४
    0.43
    Smoke
    0.43
    荡
    0.43
    nější
    0.43
    Activations Density 0.017%

    No Known Activations