© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258365
    Prev
    Next
    INDEX
    Explanations

    (if any)

    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_22_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
     Josh
    0.45
     sprechen
    0.45
    。」
    0.43
    Josh
    0.41
     হোক
    0.39
    。”
    0.39
     يتيمه
    0.39
    〕
    0.39
     根据
    0.38
     مد
    0.38
    POSITIVE LOGITS
     Citrus
    0.45
    آم
    0.43
    शरी
    0.43
    izde
    0.43
    귤
    0.41
    柑
    0.40
    utti
    0.40
    গ্রাফ
    0.40
     CFS
    0.39
     grafo
    0.39
    Activations Density 0.002%

    No Known Activations