© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236488
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
     kapital
    0.50
    ложения
    0.42
     java
    0.41
     occidentale
    0.41
     escuela
    0.39
     gemakkelijk
    0.38
     클
    0.38
     palabra
    0.38
     analizar
    0.38
    کل
    0.38
    POSITIVE LOGITS
    wic
    0.39
    ated
    0.38
    hmad
    0.36
     ጥቅም
    0.36
     Cosmetic
    0.36
    ಅ
    0.36
    ಮು
    0.35
    dehyde
    0.35
     আহমদ
    0.35
    emps
    0.34
    Activations Density 0.000%

    No Known Activations