© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 193860
    Prev
    Next
    INDEX
    Explanations

    take on the role

    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_9_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
    1
    0.44
    ’
    0.44
    ם
    0.43
     do
    0.41
    ar
    0.39
    w
    0.39
    m
    0.39
    month
    0.39
    ’।
    0.38
    2
    0.38
    POSITIVE LOGITS
     αλλά
    0.35
    ण्यासाठी
    0.35
    inals
    0.32
     revolutions
    0.32
    .
    0.32
    ifikation
    0.32
    igheten
    0.32
     μεταξύ
    0.31
     pendants
    0.31
    aties
    0.31
    Activations Density 0.003%

    No Known Activations