© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174137
    Prev
    Next
    INDEX
    Explanations

    secant line

    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_20_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
    ake
    0.38
    indahan
    0.37
     bind
    0.37
    pling
    0.35
     planted
    0.35
    romatic
    0.34
    𝘰
    0.34
    cmake
    0.34
     rag
    0.34
    planting
    0.34
    POSITIVE LOGITS
    坚
    0.39
    Elev
    0.38
     päev
    0.38
     يش
    0.38
    Students
    0.37
    式
    0.37
    School
    0.36
    學生
    0.36
     occas
    0.35
     पान
    0.35
    Activations Density 0.000%

    No Known Activations