© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 260830
    Prev
    Next
    INDEX
    Explanations

    주말

    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_5_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
    in
    1.63
    2
    1.38
    ار
    1.28
    ام
    1.20
    0
    1.19
    א
    1.18
    心
    1.10
    es
    1.09
    f
    1.09
    观
    1.05
    POSITIVE LOGITS
     aguas
    1.27
     tarefas
    1.26
     lágrimas
    1.25
     ά
    1.23
     δύο
    1.21
     ν
    1.20
     piedras
    1.20
    acciones
    1.20
     aulas
    1.17
     cajas
    1.17
    Activations Density 0.000%

    No Known Activations