© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15878
    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_40_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
     gew
    0.36
    撣
    0.36
    isTouching
    0.35
    WMN
    0.35
     creeping
    0.34
     scanning
    0.34
     quét
    0.34
     cập
    0.34
     intros
    0.33
     concentrated
    0.33
    POSITIVE LOGITS
    ಲ್ಯಾ
    0.40
     Assign
    0.40
     Tram
    0.38
     Lö
    0.38
    𝕟
    0.38
     assign
    0.38
     अमाउंट
    0.38
    捅
    0.38
    mack
    0.38
     नदी
    0.38
    Activations Density 0.000%

    No Known Activations