© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 62627
    Prev
    Next
    INDEX
    Explanations

    code block formatting

    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_41_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
     booted
    0.46
     ruck
    0.45
    宮
    0.40
     कक्षा
    0.38
    ernsey
    0.38
     kicked
    0.37
    PAL
    0.37
    节
    0.37
     Paths
    0.37
     पाल
    0.37
    POSITIVE LOGITS
    ocrine
    0.42
     Szer
    0.41
    爿
    0.38
     எழுத்த
    0.38
     illuminate
    0.36
     NZ
    0.36
     ప్రా
    0.36
     Jé
    0.36
     FIF
    0.35
     unprofessional
    0.35
    Activations Density 0.014%

    No Known Activations