© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 207321
    Prev
    Next
    INDEX
    Explanations

    variables and assignments

    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_25_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
     breathless
    0.30
     göstere
    0.30
     slideshow
    0.29
    เศษ
    0.29
    ละคร
    0.29
    썼
    0.29
     работу
    0.28
    🧨
    0.28
     цело
    0.28
     महीनों
    0.28
    POSITIVE LOGITS
    美品
    0.33
     extrémités
    0.31
     ಎಸ್
    0.31
    ERS
    0.30
    MEDIA
    0.30
     maggior
    0.30
    ersk
    0.29
    Marca
    0.29
    Ist
    0.29
    Dise
    0.29
    Activations Density 0.007%

    No Known Activations