© 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. 59081
    Prev
    Next
    INDEX
    Explanations

    deals and prices

    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
     break
    0.45
     eradicate
    0.44
     l
    0.44
     el
    0.44
     veck
    0.43
     manure
    0.43
     pesticide
    0.43
     kitchen
    0.42
     rooms
    0.42
     duplicating
    0.42
    POSITIVE LOGITS
     þei
    0.45
    okol
    0.43
     ገን
    0.42
    ventura
    0.42
    =".$
    0.41
    гр
    0.39
     لما
    0.39
    nienie
    0.39
    лат
    0.38
    ари
    0.38
    Activations Density 0.025%

    No Known Activations