© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3403
    Prev
    Next
    INDEX
    Explanations

    rings and spaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_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
    র্মে
    0.44
     daging
    0.40
     Medicines
    0.39
    bibinfo
    0.38
     tenders
    0.37
    本机
    0.37
     läk
    0.37
    싣
    0.37
     caractér
    0.37
     лікар
    0.37
    POSITIVE LOGITS
     rings
    0.44
     space
    0.42
     ring
    0.40
     graph
    0.40
     Rings
    0.39
    空间
    0.39
    Ring
    0.37
     spazio
    0.37
    Hallo
    0.36
    群
    0.36
    Activations Density 0.051%

    No Known Activations