© 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. 205222
    Prev
    Next
    INDEX
    Explanations

    was

    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
     AFRICA
    0.43
     Très
    0.42
     África
    0.41
    ⎟
    0.40
     дуже
    0.39
    Très
    0.38
     rất
    0.38
     tiện
    0.38
    pox
    0.38
     Bakın
    0.38
    POSITIVE LOGITS
    애
    0.37
     বেদ
    0.36
     grinding
    0.35
     hotspots
    0.35
     motion
    0.35
     anchors
    0.35
    VhZ
    0.35
     सेन
    0.34
    OnUiThread
    0.34
     fla
    0.34
    Activations Density 0.002%

    No Known Activations