© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 16565
    Prev
    Next
    INDEX
    Explanations

    optical fiber and communications

    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_34_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
    Optical
    1.08
     optical
    1.05
     Optical
    1.05
    光
    0.94
    光学
    0.93
     optics
    0.86
    光的
    0.85
    optical
    0.84
     光
    0.84
     Optics
    0.84
    POSITIVE LOGITS
     shq
    0.45
    mem
    0.44
     insecticide
    0.43
     Pestic
    0.42
     வேளாண்
    0.41
    Mem
    0.41
     pesticides
    0.41
     पं
    0.39
     psich
    0.39
    קט
    0.39
    Activations Density 0.006%

    No Known Activations