© 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. 141837
    Prev
    Next
    INDEX
    Explanations

    programming code setup

    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
    আত
    0.44
    PropertyParam
    0.40
    QtGui
    0.39
     outbound
    0.38
     Press
    0.38
    Press
    0.38
    றுத்த
    0.37
    爰
    0.37
    车辆
    0.37
     Antiqu
    0.37
    POSITIVE LOGITS
    шње
    0.38
     เอก
    0.36
     Xer
    0.36
     magnitude
    0.35
    が必要
    0.35
     nem
    0.35
    BJ
    0.35
    Ἡ
    0.35
    けない
    0.35
     grade
    0.34
    Activations Density 0.001%

    No Known Activations