© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82931
    Prev
    Next
    INDEX
    Explanations

    forty

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
    です
    0.36
     です
    0.34
    里
    0.33
     Япо
    0.33
     Advances
    0.33
     setUser
    0.32
    世界の
    0.32
    У
    0.32
     advances
    0.32
    lland
    0.31
    POSITIVE LOGITS
    ᱔
    0.36
     forty
    0.36
     ४
    0.35
     १८४
    0.34
    𝟰
    0.34
     trock
    0.34
    bodyParser
    0.33
    টিং
    0.33
     dryer
    0.33
     foothills
    0.32
    Activations Density 0.001%

    No Known Activations