© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 98199
    Prev
    Next
    INDEX
    Explanations

    comprehension and answering tasks

    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_14_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
    holung
    0.52
    hashtag
    0.50
    디어
    0.50
    hetto
    0.49
    쑤
    0.49
    seudo
    0.49
    ”:
    0.49
     AppModule
    0.48
    mT
    0.48
    APER
    0.48
    POSITIVE LOGITS
     daring
    0.57
     watery
    0.53
    ╞
    0.52
     yatırım
    0.52
     μαύ
    0.51
     ticaret
    0.50
     pett
    0.50
     найд
    0.49
     ήταν
    0.49
     restrained
    0.49
    Activations Density 0.054%

    No Known Activations