© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 207226
    Prev
    Next
    INDEX
    Explanations

    BJU International journal

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     సి
    0.41
    פול
    0.36
    チャ
    0.35
    cyano
    0.34
    塩
    0.34
     campeón
    0.33
     ສະ
    0.33
    イク
    0.33
     इश
    0.33
    ánicas
    0.33
    POSITIVE LOGITS
     Uber
    0.41
     Frye
    0.41
    眉头
    0.40
     amass
    0.40
     Vary
    0.39
    髯
    0.39
     ODM
    0.39
    τί
    0.38
    One
    0.38
    心中
    0.38
    Activations Density 0.000%

    No Known Activations