© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5762
    Prev
    Next
    INDEX
    Explanations

    แตกต่าง (different)

    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_40_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
    getKeyCode
    0.38
     आँख
    0.38
    ствовал
    0.38
     ذا
    0.37
     adolesc
    0.37
     anyway
    0.36
    ---------------+
    0.36
     anyways
    0.35
     Anyways
    0.35
     nitros
    0.35
    POSITIVE LOGITS
    แตกต่าง
    0.38
     risky
    0.37
    优
    0.37
    有關
    0.36
    ouard
    0.36
     berkaitan
    0.36
     bersifat
    0.35
    ियर
    0.34
    優
    0.34
     tros
    0.34
    Activations Density 0.037%

    No Known Activations