© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 203823
    Prev
    Next
    INDEX
    Explanations

    natural light

    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_46_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
     Industria
    0.39
     mounts
    0.39
    ствий
    0.38
    Table
    0.37
    
    0.36
    rawy
    0.36
    oreg
    0.36
    ▦
    0.36
    oplane
    0.35
     alarms
    0.35
    POSITIVE LOGITS
    ๋
    0.45
    的情
    0.42
     mérid
    0.39
    ServiceModel
    0.39
     monol
    0.39
     southern
    0.38
    uild
    0.38
     Cabrio
    0.38
     Aper
    0.38
    routingHeader
    0.37
    Activations Density 0.001%

    No Known Activations