© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 123347
    Prev
    Next
    INDEX
    Explanations

    mouse pad

    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_37_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
    インタ
    0.37
    Strength
    0.36
    ಂದ್ರ
    0.36
    ำ
    0.36
    ್ಯಾ
    0.36
     verifiable
    0.36
     بوص
    0.36
    Anch
    0.36
    姗
    0.35
    Technology
    0.35
    POSITIVE LOGITS
    🐀
    0.43
     rodent
    0.41
     hamster
    0.40
     họp
    0.38
    鼠
    0.37
     summon
    0.36
     rat
    0.36
    🐁
    0.36
     shields
    0.36
     गैंग
    0.36
    Activations Density 0.002%

    No Known Activations