© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133310
    Prev
    Next
    INDEX
    Explanations

    cosmic radiation, sources, or background

    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
    sheets
    1.18
    지만
    1.09
    there
    1.05
    ?
    1.03
    ו
    1.02
    ۔
    1.02
     व
    1.02
    Let
    0.97
    come
    0.92
    But
    0.91
    POSITIVE LOGITS
     for
    1.77
     as
    1.15
     from
    1.14
     kleiner
    1.14
    り
    1.12
    টি
    1.11
     usuario
    1.06
     jeu
    1.06
    ’
    1.05
    ющих
    1.03
    Activations Density 0.001%

    No Known Activations