© 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. 199288
    Prev
    Next
    INDEX
    Explanations

    boats and yachts

    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
     Innovative
    0.37
    樫
    0.37
     Desarrollo
    0.36
     realism
    0.36
     Werk
    0.35
    შინ
    0.35
    樟
    0.35
     Island
    0.34
    澳大利
    0.34
     shuffle
    0.34
    POSITIVE LOGITS
     moor
    0.38
    ddot
    0.38
     juveniles
    0.38
    dot
    0.38
     rápid
    0.38
    牟
    0.38
     peptides
    0.38
    簇
    0.37
     multimillion
    0.37
    berapa
    0.37
    Activations Density 0.001%

    No Known Activations