© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 139809
    Prev
    Next
    INDEX
    Explanations

    growing plants

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    飼
    0.41
     кілько
    0.40
    rän
    0.39
    бки
    0.38
    гой
    0.36
    㫧
    0.36
    ರೆ
    0.35
     kultur
    0.35
    тельской
    0.35
    腃
    0.35
    POSITIVE LOGITS
     ladies
    0.50
    女人
    0.46
    media
    0.45
     মেয়ে
    0.43
     женщин
    0.43
     lady
    0.42
     woman
    0.42
     women
    0.42
     media
    0.42
     girls
    0.41
    Activations Density 0.001%

    No Known Activations