© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 9492
    Prev
    Next
    INDEX
    Explanations

    technical / web context

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
     उत्ते
    0.75
     uint
    0.72
    uint
    0.69
    গৃহ
    0.69
     UIText
    0.69
    桧
    0.68
     уско
    0.68
    ћи
    0.67
    ್
    0.67
    ハイ
    0.67
    POSITIVE LOGITS
     آپ
    0.73
     Sn
    0.73
     ব্যাপকভাবে
    0.70
    Lean
    0.67
    Sn
    0.66
     affliction
    0.66
     நம்ப
    0.65
     sn
    0.64
     डाउन
    0.64
    sbom
    0.64
    Activations Density 0.115%

    No Known Activations