© 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. 141512
    Prev
    Next
    INDEX
    Explanations

    matrix

    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
     تمر
    0.49
    减
    0.42
     diminuer
    0.40
    ụt
    0.38
    緩和
    0.38
    ດ
    0.38
    集中
    0.36
    靈
    0.36
    mad
    0.36
     Corresponding
    0.36
    POSITIVE LOGITS
    संख्यक
    0.43
    olič
    0.40
    sanitize
    0.37
    ôtels
    0.36
    नावश्यक
    0.36
    峮
    0.35
    uniqueItems
    0.35
    啡
    0.35
    ರಿಂದ
    0.35
    ピュー
    0.35
    Activations Density 0.001%

    No Known Activations