© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60616
    Prev
    Next
    INDEX
    Explanations

    worn down

    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_11_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
    ↵↵
    0.61
    to
    0.58
     '>
    0.57
    9
    0.53
    the
    0.52
    ে
    0.52
    )
    0.52
    temperature
    0.50
    0.50
    M
    0.50
    POSITIVE LOGITS
     MACHIN
    0.66
    ¹,
    0.62
    aço
    0.62
     каждом
    0.61
     በእ
    0.61
     luminal
    0.60
    скому
    0.59
    ţie
    0.59
    每一個
    0.59
     inwardly
    0.59
    Activations Density 0.001%

    No Known Activations