© 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. 159586
    Prev
    Next
    INDEX
    Explanations

    Spanish words like el, algo, horario

    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
     are
    0.78
     as
    0.76
    la
    0.68
    r
    0.66
    ري
    0.65
    á
    0.64
    lger
    0.60
    ah
    0.60
    ল
    0.60
    را
    0.57
    POSITIVE LOGITS
    B
    1.00
     it
    0.97
    M
    0.95
    P
    0.91
    R
    0.89
    D
    0.86
    W
    0.84
    K
    0.84
    H
    0.84
     a
    0.84
    Activations Density 0.000%

    No Known Activations