© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90467
    Prev
    Next
    INDEX
    Explanations

    formulate

    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_11_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
    າດ
    0.69
    اري
    0.68
    يني
    0.68
    ၅
    0.66
    یدی
    0.66
    وي
    0.64
    проце
    0.64
    ید
    0.63
     iniz
    0.63
    ка
    0.62
    POSITIVE LOGITS
     modules
    0.59
     ang
    0.59
    en
    0.58
     ligands
    0.57
    ↵↵
    0.57
     sand
    0.56
     plugins
    0.56
     liga
    0.56
    ل
    0.56
     aflat
    0.55
    Activations Density 0.002%

    No Known Activations