© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78675
    Prev
    Next
    INDEX
    Explanations

    personal information and contexts

    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_0_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
    ي
    2.52
    ه
    2.48
    י
    2.34
    i
    2.19
    ت
    2.19
    ה
    2.03
    ス
    1.99
    ი
    1.94
    ج
    1.93
    س
    1.84
    POSITIVE LOGITS
    <0x80>
    1.20
    ů
    1.17
    ight
    1.14
    人不
    1.13
    abá
    1.10
    䍜
    1.07
    ishes
    1.06
     není
    1.05
    必定
    1.05
    ův
    1.04
    Activations Density 0.003%

    No Known Activations