© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124854
    Prev
    Next
    INDEX
    Explanations

    base salary and parameters

    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_3_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
     base
    0.65
    馇
    0.61
    基于
    0.60
    ถาน
    0.60
    gning
    0.57
    ᑉ
    0.56
     recus
    0.55
    ૩
    0.55
     concaten
    0.55
     paramount
    0.54
    POSITIVE LOGITS
    ());
    0.68
    </h1>
    0.64
    ,’
    0.55
    ,’”
    0.55
    י
    0.55
    жда
    0.54
    యిత
    0.54
    archie
    0.53
    ast
    0.53
    AH
    0.52
    Activations Density 0.003%

    No Known Activations