© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 180572
    Prev
    Next
    INDEX
    Explanations

    flow rate or discount

    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_29_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
    优势
    0.35
    将于
    0.35
     ciclos
    0.35
     불구하고
    0.35
     Moritz
    0.35
     ciclo
    0.34
     unequal
    0.34
    륵
    0.34
    นาย
    0.34
     Blot
    0.33
    POSITIVE LOGITS
    cal
    0.38
    inars
    0.38
     haven
    0.36
    chal
    0.35
    inar
    0.35
     wouldn
    0.34
    ine
    0.34
    uhan
    0.34
    oir
    0.33
    cc
    0.32
    Activations Density 0.002%

    No Known Activations