© 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. 65305
    Prev
    Next
    INDEX
    Explanations

    announcements and actions

    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
    备份
    0.42
     backup
    0.41
    backup
    0.40
     commercially
    0.39
    呼
    0.38
    公开
    0.38
     презен
    0.36
    QRect
    0.35
    subarray
    0.35
    byteArray
    0.35
    POSITIVE LOGITS
     ड
    0.49
     gather
    0.45
     gathering
    0.43
    ve
    0.42
    晦
    0.41
     BN
    0.40
    kuje
    0.40
    VE
    0.39
     වී
    0.39
    Ve
    0.38
    Activations Density 0.000%

    No Known Activations