© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220673
    Prev
    Next
    INDEX
    Explanations

    archiveofourown.org tags or similar metadata

    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_31_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
     طبق
    0.44
     almacenar
    0.39
     bottling
    0.36
    ეკ
    0.36
    癃
    0.36
     amounts
    0.35
    zers
    0.34
    Jamie
    0.34
     paperwork
    0.34
     Janet
    0.34
    POSITIVE LOGITS
    并未
    0.41
    бле
    0.40
     *_
    0.39
    英雄
    0.37
     protagonista
    0.37
     দিয়া
    0.36
     tritt
    0.36
     문제
    0.36
    σωπ
    0.36
     kerül
    0.36
    Activations Density 0.001%

    No Known Activations