© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91707
    Prev
    Next
    INDEX
    Explanations

    air act damage

    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_11_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
     rum
    0.54
     boiler
    0.53
     cheeky
    0.46
    itching
    0.46
     brewery
    0.46
     rij
    0.46
     administers
    0.46
     并
    0.45
     serio
    0.45
     retelling
    0.45
    POSITIVE LOGITS
    いくつかの
    0.52
     Pseudomonas
    0.48
     Pyaar
    0.47
     Relationships
    0.47
     Faisal
    0.47
    aisal
    0.46
    Prox
    0.46
    یند
    0.45
     Pseudo
    0.45
    ﻈ
    0.45
    Activations Density 0.005%

    No Known Activations