© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80976
    Prev
    Next
    INDEX
    Explanations

    Japanese

    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
     अन्त
    0.45
    ermen
    0.44
    咊
    0.39
    pperware
    0.38
     எடு
    0.38
    იმე
    0.37
     Amendment
    0.37
     இன்
    0.37
    yki
    0.37
    ヌ
    0.36
    POSITIVE LOGITS
     bieg
    0.41
     Son
    0.39
     сон
    0.38
     chock
    0.38
     candidate
    0.38
     Се
    0.38
    Josh
    0.37
     Josh
    0.37
     bit
    0.36
    chall
    0.36
    Activations Density 0.008%

    No Known Activations