© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166020
    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_31_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
    dell
    0.42
    equiv
    0.40
    ̴
    0.38
    combin
    0.38
     hafta
    0.37
    nature
    0.37
     bü
    0.37
     klim
    0.36
     পঞ্চাশ
    0.35
    aldi
    0.35
    POSITIVE LOGITS
    陋
    0.40
    ANCES
    0.39
     Console
    0.38
     corpus
    0.37
    жон
    0.37
     Radiology
    0.37
    REF
    0.37
     Families
    0.37
     chiff
    0.36
    煒
    0.36
    Activations Density 0.000%

    No Known Activations