© 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. 123187
    Prev
    Next
    INDEX
    Explanations

    algorithm indices 2d arrays

    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
    ylobacter
    0.39
     kati
    0.39
    棱
    0.39
     Fatty
    0.38
    漪
    0.38
    濁
    0.38
     HCC
    0.37
    Silence
    0.37
    HCC
    0.37
     announc
    0.36
    POSITIVE LOGITS
     mural
    0.50
     murals
    0.49
     bas
    0.47
    壁
    0.46
     ceiling
    0.46
     벽
    0.45
     wall
    0.44
     painting
    0.42
     panels
    0.40
    ceiling
    0.40
    Activations Density 0.002%

    No Known Activations