© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232255
    Prev
    Next
    INDEX
    Explanations

    getting user input via prompt

    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_32_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    뺀
    0.42
    ệnh
    0.41
    exclude
    0.38
     अपन
    0.38
    nemidophorus
    0.35
    cludes
    0.35
     الحكم
    0.34
     VARCHAR
    0.34
    createQuery
    0.34
    (':
    0.34
    POSITIVE LOGITS
     arriver
    0.39
     Aha
    0.39
     Smartphone
    0.38
     Realistic
    0.38
     Fonseca
    0.38
     Immediate
    0.37
     thanking
    0.37
     IMMEDIATE
    0.37
     Tate
    0.36
     Maximal
    0.36
    Activations Density 0.001%

    No Known Activations