© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207010
    Prev
    Next
    INDEX
    Explanations

    classification and exemptions

    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
    腕
    0.41
     Rotary
    0.41
    但他
    0.41
     وسهلا
    0.40
    คู่
    0.40
    าม
    0.39
    分类
    0.39
     gliding
    0.39
    隶
    0.39
     wear
    0.39
    POSITIVE LOGITS
     Adjustment
    0.45
    Adjustment
    0.43
    Ⲱ
    0.43
    gore
    0.43
     Possibly
    0.41
    adjustment
    0.40
     வெளிப்புற
    0.39
    ዴት
    0.39
    WithObjects
    0.38
    ccccn
    0.38
    Activations Density 0.000%

    No Known Activations