© 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. 159817
    Prev
    Next
    INDEX
    Explanations

    быть + adjective/adverb

    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
    em
    0.94
    (
    0.92
    a
    0.84
    0.81
    é
    0.81
    <0xA0>
    0.81
    ри
    0.79
    r
    0.78
    <0xBF>
    0.77
    <0x80>
    0.76
    POSITIVE LOGITS
    ب
    1.12
     adsorb
    1.09
     reinterpret
    1.05
    あ
    1.03
    തി
    1.02
    ن
    1.02
    ک
    0.98
     intento
    0.98
     envio
    0.98
     invigor
    0.96
    Activations Density 0.000%

    No Known Activations