© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165435
    Prev
    Next
    INDEX
    Explanations

    shiki

    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_13_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
     Ideas
    0.50
     മാത്രം
    0.45
     ر
    0.44
    撂
    0.43
     ideas
    0.42
    狭
    0.42
    飽
    0.40
    整
    0.39
     $
    0.38
    栏
    0.38
    POSITIVE LOGITS
     japones
    0.56
     averse
    0.51
     japonés
    0.48
    ди
    0.48
     Verificar
    0.47
    belum
    0.47
     japonais
    0.47
    ➲
    0.47
     coleta
    0.46
     aparel
    0.46
    Activations Density 0.001%

    No Known Activations