© 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. 180064
    Prev
    Next
    INDEX
    Explanations

    following weekend, LP, contact information

    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
    ReadLine
    0.39
    엑
    0.38
    桌面
    0.37
    《
    0.37
    )])
    0.37
     косми
    0.36
     экстра
    0.35
     रुपया
    0.34
     пропа
    0.34
    بيك
    0.34
    POSITIVE LOGITS
     inhabiting
    0.42
    ählte
    0.40
     nhiễm
    0.38
    ungere
    0.38
    lden
    0.38
     رہتے
    0.37
    ীয়তে
    0.37
     degener
    0.37
    ń
    0.37
     inhabitants
    0.36
    Activations Density 0.000%

    No Known Activations