© 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. 40741
    Prev
    Next
    INDEX
    Explanations

    path.join(

    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
    ader
    0.68
    {\
    0.59
    Anders
    0.58
    arel
    0.57
    army
    0.56
    beliefs
    0.56
    appeal
    0.56
    }{\
    0.55
    ander
    0.55
    aders
    0.54
    POSITIVE LOGITS
    ↵
    0.62
     this
    0.60
    urilor
    0.59
     curto
    0.58
     conduire
    0.57
    то
    0.56
     îi
    0.55
     titulado
    0.55
     то
    0.54
     jargon
    0.52
    Activations Density 0.016%

    No Known Activations