© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2502
    Prev
    Next
    INDEX
    Explanations

    stories and tales

    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_40_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
    烝
    0.34
    餑
    0.34
    وز
    0.34
     Mental
    0.32
    Hope
    0.32
     наде
    0.32
     Наде
    0.32
    嵬
    0.30
     Tutorial
    0.29
    洺
    0.29
    POSITIVE LOGITS
     stories
    1.61
    Stories
    1.39
    stories
    1.38
     tales
    1.38
     Stories
    1.36
     STORIES
    1.29
     storie
    1.27
     story
    1.22
     कहान
    1.19
     historias
    1.18
    Activations Density 0.061%

    No Known Activations