© 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. 81735
    Prev
    Next
    INDEX
    Explanations

    using

    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
     kep
    0.45
     Mortgage
    0.40
    ائق
    0.38
    惠
    0.38
     eset
    0.37
     Col
    0.37
    ಿಸ
    0.37
     кере
    0.37
    滁
    0.37
     pequ
    0.36
    POSITIVE LOGITS
    Nas
    1.48
     Nas
    1.47
    nas
    1.40
     nas
    1.38
     NAS
    1.31
    NAS
    1.30
    Nash
    1.17
     Nash
    1.16
     nasal
    1.08
     Nass
    1.04
    Activations Density 0.001%

    No Known Activations