© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 181555
    Prev
    Next
    INDEX
    Explanations

    law or decision numbers and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_29_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
    ⠉
    0.35
    Several
    0.35
    ரே
    0.35
    Beer
    0.34
    sx
    0.34
    Port
    0.34
    ખો
    0.34
    いくつか
    0.34
     Port
    0.34
     Edison
    0.33
    POSITIVE LOGITS
     λόγω
    0.40
     ब्रो
    0.39
    ]').
    0.39
     sanded
    0.38
     paragra
    0.38
     சிறு
    0.37
     renverse
    0.37
     बिकॉज
    0.37
     module
    0.37
     Adjustable
    0.37
    Activations Density 0.000%

    No Known Activations