© 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. 82330
    Prev
    Next
    INDEX
    Explanations

    development

    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
    Worldwide
    0.44
    Quem
    0.40
     全部
    0.40
    암
    0.40
     odp
    0.37
    ಲಿಯ
    0.37
    dtd
    0.36
    itee
    0.36
    জিও
    0.36
    ዶ
    0.36
    POSITIVE LOGITS
     Robbie
    0.43
     सो
    0.41
     tabpos
    0.41
    摇
    0.40
     સો
    0.39
    ServiceModel
    0.39
     Soh
    0.39
    issati
    0.38
     Sop
    0.38
     Hugh
    0.37
    Activations Density 0.001%

    No Known Activations