© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245438
    Prev
    Next
    INDEX
    Explanations

    physical hardware components

    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
    цени
    0.38
    娥
    0.37
    ouri
    0.37
    OND
    0.37
     autori
    0.37
     받을
    0.36
     Urine
    0.36
     abd
    0.36
    register
    0.35
     energii
    0.35
    POSITIVE LOGITS
    宿舍
    0.38
    )],
    0.36
    ../../../
    0.36
     kapp
    0.36
    Analy
    0.36
    Caption
    0.35
    ам
    0.35
    ลักษณะ
    0.35
     হোট
    0.34
    넌
    0.34
    Activations Density 0.003%

    No Known Activations