© 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. 67387
    Prev
    Next
    INDEX
    Explanations

    September

    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
     موارد
    0.39
    िफिकेशन
    0.38
    ErrorInfo
    0.37
     ance
    0.36
    oire
    0.35
    Garage
    0.35
    െന്ന
    0.34
    </th>
    0.34
    Proguard
    0.34
    眷
    0.34
    POSITIVE LOGITS
     ২০২২
    0.49
     २०२२
    0.48
     August
    0.48
     HHS
    0.46
     ২০২১
    0.45
     FY
    0.44
     अगस्त
    0.44
     ২০১৯
    0.43
     CY
    0.42
     Pictures
    0.42
    Activations Density 0.002%

    No Known Activations