© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 91776
    Prev
    Next
    INDEX
    Explanations

    learning objectives

    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
     at
    0.63
    iano
    0.60
     .
    0.56
    ard
    0.55
     are
    0.54
     argued
    0.53
    ade
    0.52
    ía
    0.52
    ology
    0.50
    .</
    0.50
    POSITIVE LOGITS
    padă
    0.65
    Ἥ
    0.59
     매출
    0.59
     metamorph
    0.58
     jūn
    0.58
    功率
    0.57
     Antennes
    0.57
     Lieblings
    0.56
     வகையில்
    0.56
    ла
    0.55
    Activations Density 0.004%

    No Known Activations