© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261254
    Prev
    Next
    INDEX
    Explanations

    webpage structure and content

    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
    0
    1.38
     முறையில்
    1.23
    haal
    1.06
    lerce
    1.04
    hran
    1.02
    filtration
    1.01
    hrad
    1.00
    ̀i
    0.99
    <0x80>
    0.98
    hardening
    0.98
    POSITIVE LOGITS
    t
    1.85
    ل
    1.41
     it
    1.38
    it
    1.33
    l
    1.26
    ä
    1.17
    ด
    1.16
     I
    1.12
    िंग
    1.11
     l
    1.10
    Activations Density 0.001%

    No Known Activations