© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 162899
    Prev
    Next
    INDEX
    Explanations

    LINQ lambdas

    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_31_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
     DeepCollection
    0.35
    愺
    0.35
    lastval
    0.34
    洨
    0.33
    ElementException
    0.33
     ہوج
    0.32
     మాట్లాడుతూ
    0.32
    㐸
    0.31
    Outlet
    0.31
    Slots
    0.31
    POSITIVE LOGITS
     iOS
    0.37
     NL
    0.36
    android
    0.36
     Xcode
    0.35
     Chlor
    0.35
    NL
    0.34
     Sentiment
    0.34
     Android
    0.34
     chlorine
    0.33
     acid
    0.33
    Activations Density 0.003%

    No Known Activations