© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 221059
    Prev
    Next
    INDEX
    Explanations

    Helen Keller or RA adapter

    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_10_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
    </strong>
    0.68
     याबाबत
    0.61
     senator
    0.61
     tiger
    0.56
     था
    0.55
     note
    0.55
     Duchess
    0.55
     tuk
    0.54
     yanı
    0.54
     reproach
    0.52
    POSITIVE LOGITS
    ד
    0.67
    ά
    0.66
    бычно
    0.65
     opér
    0.64
     formes
    0.61
     válv
    0.61
    달
    0.60
     Conseils
    0.58
    ш
    0.58
     manifolds
    0.58
    Activations Density 0.001%

    No Known Activations