© 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. 179335
    Prev
    Next
    INDEX
    Explanations

    code constructs, punctuation

    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
     meski
    0.41
    Ꭻ
    0.38
    即便
    0.38
    煊
    0.38
     apesar
    0.38
    endra
    0.37
    Hyper
    0.37
    사는
    0.37
     displayName
    0.36
     করলেও
    0.36
    POSITIVE LOGITS
     、,
    0.45
    または
    0.37
     °,
    0.36
     espírito
    0.36
    イール
    0.35
     Москве
    0.35
     parked
    0.34
     †
    0.33
     Laut
    0.33
    ₽
    0.33
    Activations Density 0.003%

    No Known Activations