© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92479
    Prev
    Next
    INDEX
    Explanations

    Grace Hopper

    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_11_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
    ")}}
    0.51
     स्थान
    0.50
     Pencil
    0.50
     Folgen
    0.49
     පේශ
    0.49
    СТ
    0.48
    앓
    0.48
     الليل
    0.47
    Liens
    0.46
    ‌است
    0.45
    POSITIVE LOGITS
    '
    0.58
     '
    0.51
     (
    0.49
    user
    0.47
    τε
    0.43
     barriers
    0.43
     unambiguous
    0.43
     conformations
    0.43
     annotation
    0.43
     contexts
    0.42
    Activations Density 0.000%

    No Known Activations