© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176041
    Prev
    Next
    INDEX
    Explanations

    **Presidential last names**

    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_24_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
    同行
    0.48
     cumin
    0.44
    umeric
    0.42
    lename
    0.41
    擎
    0.41
    新
    0.40
     ENGINE
    0.40
     चिर
    0.39
     menos
    0.38
    engine
    0.38
    POSITIVE LOGITS
     Deputies
    0.43
     Unternehmens
    0.38
     Leinster
    0.38
     بیماری
    0.37
     Jesuits
    0.37
    мой
    0.37
     být
    0.37
    囿
    0.36
     Lieutenant
    0.36
    겅
    0.35
    Activations Density 0.001%

    No Known Activations