© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210857
    Prev
    Next
    INDEX
    Explanations

    kyiv, Sachertorte, Sac

    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_5_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
    एम
    1.16
     ہوگا۔
    1.08
    ᱐
    1.06
     होगा
    1.05
    ツール
    1.05
     Уен
    1.03
    एस
    1.00
     activid
    1.00
    chts
    1.00
     acus
    1.00
    POSITIVE LOGITS
    ת
    1.81
    ה
    1.73
    น
    1.52
    /
    1.51
    ت
    1.47
    י
    1.47
    د
    1.46
    ن
    1.44
    א
    1.41
    ט
    1.38
    Activations Density 0.000%

    No Known Activations