© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1761
    Prev
    Next
    INDEX
    Explanations

    specific markers following text

    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_39_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
    TPP
    0.39
     ক্ষতির
    0.38
     상당
    0.36
     इत्यादी
    0.35
    แมนเชสเตอร์ซิตี
    0.34
    𒁕
    0.34
    であ
    0.34
    TPS
    0.33
    riso
    0.33
    𒋫
    0.33
    POSITIVE LOGITS
     Van
    0.36
     ராஜா
    0.35
     Buxton
    0.35
    nia
    0.34
     Agency
    0.34
     Vans
    0.34
     Des
    0.33
     Id
    0.33
     Ages
    0.33
    nač
    0.32
    Activations Density 1.178%

    No Known Activations