© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166678
    Prev
    Next
    INDEX
    Explanations

    knowledge management systems

    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_31_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
    尃
    0.36
    uyên
    0.36
     fleets
    0.35
    MR
    0.34
    Codes
    0.33
    㞔
    0.33
     Dram
    0.33
     firmy
    0.32
    Squad
    0.32
    搬型
    0.31
    POSITIVE LOGITS
     एक्सेल
    0.40
     Wiki
    0.38
     XLS
    0.37
    狯
    0.37
     Wordpress
    0.36
     interference
    0.36
     지
    0.35
    蟀
    0.35
     toggle
    0.35
     अनुराग
    0.35
    Activations Density 0.008%

    No Known Activations