© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41246
    Prev
    Next
    INDEX
    Explanations

    ID, IP addresses, numbers, position qualifiers

    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_22_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
     이름을
    0.47
     имя
    0.46
     Inggris
    0.46
     제목
    0.46
     judul
    0.45
     영어
    0.45
    కర్
    0.44
     keywords
    0.44
     이름
    0.43
    ў
    0.43
    POSITIVE LOGITS
    Household
    0.45
    OTP
    0.44
    hatta
    0.44
    ሳት
    0.42
    OLD
    0.41
    Passenger
    0.41
    Nurse
    0.40
    IPT
    0.39
    الط
    0.38
    LongNumber
    0.38
    Activations Density 0.015%

    No Known Activations