© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 125404
    Prev
    Next
    INDEX
    Explanations

    OutlineInputBorder, Date, document

    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_37_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
     GRANT
    0.46
     बताएं
    0.43
     EXISTS
    0.40
    长江
    0.40
     Chuck
    0.40
     Treats
    0.39
     Đồng
    0.39
    暝
    0.39
     ét
    0.39
    যুব
    0.38
    POSITIVE LOGITS
     kamm
    0.39
     കമ്മി
    0.37
     couple
    0.37
    couple
    0.37
    cooled
    0.37
    when
    0.36
    fft
    0.36
     калі
    0.36
    ESA
    0.35
    input
    0.34
    Activations Density 0.000%

    No Known Activations