© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 100480
    Prev
    Next
    INDEX
    Explanations

    Synthesia AI video generation

    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_16_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
     separating
    0.52
    <0x0D>
    0.49
     θε
    0.48
    分开
    0.47
     kth
    0.47
    位于
    0.47
     judge
    0.46
     типи
    0.46
     해석
    0.46
     opérateur
    0.45
    POSITIVE LOGITS
     salads
    0.52
     acceso
    0.51
    emas
    0.50
    ᱕
    0.49
     dupa
    0.49
     tuvimos
    0.48
     tablets
    0.47
    anlı
    0.46
    、“
    0.46
     parar
    0.46
    Activations Density 0.002%

    No Known Activations