© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201161
    Prev
    Next
    INDEX
    Explanations

    document parts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    龅
    0.39
     ок
    0.39
     Alright
    0.39
     попула
    0.38
     ok
    0.38
     polyn
    0.37
     polygonal
    0.37
     okay
    0.37
    Asalamualaikum
    0.37
    颶
    0.37
    POSITIVE LOGITS
     ends
    0.39
    Hardware
    0.37
    肘
    0.37
    কারি
    0.37
    Tema
    0.35
    تل
    0.34
     introduces
    0.34
    mData
    0.34
    extractor
    0.34
    скому
    0.33
    Activations Density 0.001%

    No Known Activations