© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 178753
    Prev
    Next
    INDEX
    Explanations

    other times

    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_29_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
     যুক্তরাষ্ট্রে
    0.39
    denominator
    0.38
    ⇄
    0.38
    izione
    0.37
     Neumann
    0.37
     traigo
    0.37
    ட்டில்
    0.37
    😺
    0.37
     Tyler
    0.36
     Parisian
    0.36
    POSITIVE LOGITS
    エム
    0.40
     deems
    0.36
    roughly
    0.34
     औ
    0.34
    माया
    0.34
     glitches
    0.34
     kole
    0.34
     الجديدة
    0.33
    ématiques
    0.33
    更为
    0.33
    Activations Density 0.001%

    No Known Activations