© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218121
    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
     Sno
    0.39
     incubator
    0.36
     yena
    0.35
    샛
    0.35
     hadiah
    0.34
    erry
    0.33
    섹
    0.33
     관련
    0.33
    ホース
    0.33
     disappoint
    0.33
    POSITIVE LOGITS
    ictwa
    0.39
    Abr
    0.36
     staff
    0.36
     comforts
    0.36
     जलन
    0.35
     undoubt
    0.35
     irritability
    0.34
     refractory
    0.34
     πάνω
    0.34
    年至
    0.34
    Activations Density 0.000%

    No Known Activations