© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136535
    Prev
    Next
    INDEX
    Explanations

    waterproof leaves, writing tablet

    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_12_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
    YouTube
    0.42
    Alphabet
    0.40
    Muchas
    0.40
    Theatre
    0.38
     کوتاه
    0.38
     دوبارہ
    0.37
    ╣
    0.37
    TakeVideo
    0.37
    ्यारह
    0.37
     방정식
    0.37
    POSITIVE LOGITS
     sobre
    0.41
     so
    0.41
     rattling
    0.39
     мной
    0.38
     nhiễm
    0.38
     what
    0.37
     intox
    0.37
    ی
    0.37
    ra
    0.36
     поддержи
    0.36
    Activations Density 0.001%

    No Known Activations