© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39719
    Prev
    Next
    INDEX
    Explanations

    often followed by verbs (have, difficult, introduced, suggest, overly, contains, wants, claimed)

    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
    اك
    0.61
    aas
    0.61
    ்களுக்கு
    0.56
     incertid
    0.53
    ا
    0.53
    ໜ
    0.53
     أك
    0.52
    ){
    0.52
    टीएम
    0.52
    ்ப்ப
    0.52
    POSITIVE LOGITS
    Austral
    0.57
    1
    0.55
     Sweden
    0.55
     résulte
    0.55
    3
    0.54
    逋
    0.54
    Japan
    0.53
    года
    0.52
     Australia
    0.52
     Prevention
    0.51
    Activations Density 0.000%

    No Known Activations