© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12207
    Prev
    Next
    INDEX
    Explanations

    XML declarations and tags

    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_40_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
     Ç
    0.40
    🫡
    0.38
     ç
    0.38
    を高
    0.37
    Ç
    0.37
    çay
    0.37
     گے۔
    0.36
     ultricies
    0.36
     статистики
    0.36
    呵呵
    0.36
    POSITIVE LOGITS
     believer
    0.41
    ポリ
    0.39
     polyp
    0.38
     Polyp
    0.38
    belle
    0.38
    籶
    0.37
     pól
    0.37
     বিশ্বাস
    0.36
    caya
    0.36
    бира
    0.35
    Activations Density 0.001%

    No Known Activations