© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 203001
    Prev
    Next
    INDEX
    Explanations

    write article essay story summary

    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_12_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
    javab
    0.23
    X
    0.23
    smallest
    0.22
    ナチュラル
    0.21
    Neurons
    0.21
    >"
    0.21
     ब्लॉ
    0.21
    ട്
    0.21
    "，
    0.20
    NavigationView
    0.20
    POSITIVE LOGITS
    垪
    0.23
     militaire
    0.22
     الك
    0.21
     leite
    0.21
     Raquel
    0.20
     Queste
    0.20
     alkyl
    0.20
     metade
    0.20
     chimique
    0.20
     mobil
    0.19
    Activations Density 0.003%

    No Known Activations