© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 68900
    Prev
    Next
    INDEX
    Explanations

    text editor features

    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
     Duluth
    0.44
    霏
    0.43
    工具
    0.41
     dbcontext
    0.41
     ...]
    0.39
     blackboard
    0.39
     Ginkuhà
    0.38
     cadre
    0.38
    уна
    0.37
     இழு
    0.36
    POSITIVE LOGITS
    Encoder
    0.37
     colonists
    0.36
    ریان
    0.36
     तलाश
    0.36
    പ്പോഴ
    0.36
    孃
    0.35
     পশ্চিমা
    0.35
    பு
    0.35
    jc
    0.35
    ofs
    0.35
    Activations Density 0.005%

    No Known Activations