© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3800
    Prev
    Next
    INDEX
    Explanations

    concepts and structures

    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_39_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
    SYSTEM
    0.21
    System
    0.20
     System
    0.20
    工作
    0.20
     ------------
    0.19
    Respons
    0.18
     Saj
    0.18
    Master
    0.18
     Sự
    0.18
     Polo
    0.18
    POSITIVE LOGITS
    ('$(
    0.23
     conund
    0.23
     चुनौतियों
    0.22
    bracketing
    0.20
     chapitre
    0.20
     girdle
    0.20
    قیه
    0.20
     ငါ
    0.19
    峽
    0.19
    ेट्टी
    0.19
    Activations Density 0.398%

    No Known Activations