© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11932
    Prev
    Next
    INDEX
    Explanations

    visitation and academy

    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_40_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
     frontend
    0.44
    ྜ
    0.41
    濕
    0.39
     negatives
    0.38
    溧
    0.38
     Frontend
    0.37
    Dining
    0.37
    蒎
    0.37
     شاید
    0.36
     humides
    0.36
    POSITIVE LOGITS
    ("@
    0.39
     ヨ
    0.37
    ORITY
    0.37
    iban
    0.35
    ONA
    0.35
     인천
    0.34
    AboutDlg
    0.34
     nx
    0.34
    зяржа
    0.34
    olecules
    0.33
    Activations Density 0.001%

    No Known Activations