© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43202
    Prev
    Next
    INDEX
    Explanations

    merge... on

    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_22_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
     fermé
    0.45
    unities
    0.44
     égal
    0.44
    oretical
    0.43
     tensão
    0.43
    
    0.42
    \";
    0.42
     bias
    0.41
    \":
    0.41
    ším
    0.41
    POSITIVE LOGITS
     sat
    0.44
    a
    0.43
    ه‌
    0.42
     Guaranteed
    0.41
    anta
    0.41
    sat
    0.40
    ik
    0.39
    дут
    0.39
    િક
    0.38
    owe
    0.38
    Activations Density 0.008%

    No Known Activations