© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154589
    Prev
    Next
    INDEX
    Explanations

    error handling

    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_23_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
     authentic
    0.40
     featured
    0.40
     scare
    0.40
     and
    0.39
     wares
    0.39
     সত্যিকারের
    0.39
     NET
    0.39
     frantic
    0.38
    廡
    0.38
     won
    0.38
    POSITIVE LOGITS
    TableAdapter
    0.41
     evapor
    0.40
     Komis
    0.40
     coordinadora
    0.39
    BankAccount
    0.38
    ("-"*
    0.37
     табу
    0.37
     которую
    0.37
     LUMPUR
    0.36
    maxlen
    0.36
    Activations Density 0.003%

    No Known Activations