© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38721
    Prev
    Next
    INDEX
    Explanations

    seaborn and matplotlib plots

    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_11_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
    Color
    0.65
    Pictures
    0.59
    says
    0.56
    водится
    0.55
    T
    0.55
    St
    0.55
    Steps
    0.55
    Se
    0.54
    Cl
    0.54
    اره
    0.54
    POSITIVE LOGITS
     ayatan
    0.59
     ou
    0.57
     Ashland
    0.55
     Oahu
    0.52
     Oeste
    0.52
     Balkan
    0.52
     크라운
    0.51
    ä
    0.51
     öğret
    0.51
    !”,
    0.51
    Activations Density 0.023%

    No Known Activations