© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209254
    Prev
    Next
    INDEX
    Explanations

    attention-seeking behavior

    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_20_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
    🎲
    0.26
    RefreshToken
    0.25
     proyecto
    0.23
     justo
    0.22
    proyecto
    0.22
     Proyecto
    0.22
    Stretch
    0.22
     frosty
    0.22
    GORITHM
    0.22
     Ejemplo
    0.22
    POSITIVE LOGITS
     мили
    0.25
    异
    0.24
     blockage
    0.23
     విద్య
    0.23
    闹
    0.22
     агре
    0.22
    విద్య
    0.21
     adherents
    0.21
    ху
    0.21
     ความ
    0.21
    Activations Density 0.002%

    No Known Activations