© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159765
    Prev
    Next
    INDEX
    Explanations

    expire / espera expiration

    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
    는
    1.30
    は
    1.22
    is
    1.12
    是
    1.08
    <0x80>
    0.99
    are
    0.84
    А
    0.84
    的
    0.84
    мо
    0.80
     decimated
    0.79
    POSITIVE LOGITS
    ,
    0.99
    ่
    0.84
    ti
    0.79
     undang
    0.78
    ha
    0.77
    tn
    0.77
    till
    0.75
     e
    0.75
    तः
    0.75
    tl
    0.69
    Activations Density 0.001%

    No Known Activations