© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18703
    Prev
    Next
    INDEX
    Explanations

    aws, azure, java, management, console, cli, portal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_34_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
     bare
    0.43
     ureth
    0.39
     scrub
    0.38
     culture
    0.38
    裸
    0.37
     abstract
    0.37
     compelling
    0.37
     lost
    0.36
     ecc
    0.36
     urea
    0.36
    POSITIVE LOGITS
     SHALL
    0.44
     BOU
    0.44
     जावा
    0.39
    Bou
    0.38
    定向
    0.38
     হত্যাকাণ্ড
    0.37
    Java
    0.36
    ~~~~~~~~~~~~~~~~
    0.36
    ToJava
    0.36
     হত্যাকা
    0.35
    Activations Density 0.060%

    No Known Activations