© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7052
    Prev
    Next
    INDEX
    Explanations

    month day year

    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_40_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
     Fast
    0.39
    cas
    0.38
    Bj
    0.37
    quero
    0.37
     Pig
    0.36
     Flesh
    0.36
     exec
    0.36
    谿
    0.36
     rush
    0.36
    umls
    0.36
    POSITIVE LOGITS
     रोजी
    0.41
     Tartu
    0.38
    सीएस
    0.38
     отмеча
    0.37
    प्रिंट
    0.36
     jl
    0.35
     dill
    0.35
     côn
    0.35
    lever
    0.34
    ūd
    0.34
    Activations Density 0.019%

    No Known Activations