© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165071
    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_13_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
     изменя
    0.53
     cambi
    0.52
     vasena
    0.50
     změ
    0.50
    ,"$
    0.48
    ,}
    0.48
    ével
    0.47
     incênd
    0.47
    iril
    0.46
    шение
    0.46
    POSITIVE LOGITS
    AD
    0.55
     Ferr
    0.55
    Ferr
    0.54
    Sodium
    0.54
    Now
    0.53
    them
    0.49
    ন
    0.49
    Streak
    0.48
    Yay
    0.48
    Not
    0.48
    Activations Density 0.000%

    No Known Activations