© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 244963
    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
     Meaning
    0.37
     Fakt
    0.37
    앗
    0.37
     message
    0.36
     NA
    0.36
     satisfy
    0.35
     Fa
    0.35
     Shout
    0.35
     SA
    0.34
     ضرب
    0.34
    POSITIVE LOGITS
    itele
    0.42
    льність
    0.41
     קי
    0.39
    urig
    0.38
    ゜
    0.38
    ৤
    0.38
    paris
    0.37
     reformers
    0.37
     كي
    0.37
    केर
    0.37
    Activations Density 0.000%

    No Known Activations