© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 244641
    Prev
    Next
    INDEX
    Explanations

    smooth transition during departure

    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
    Ask
    0.44
     ask
    0.43
    ASK
    0.43
     ASK
    0.41
     pouvaient
    0.41
     能
    0.40
     podía
    0.39
    Forecast
    0.39
     Можно
    0.38
     Ask
    0.38
    POSITIVE LOGITS
     շ
    0.38
     ক্যাপ
    0.37
    釐
    0.37
    orylation
    0.37
     dile
    0.36
    addin
    0.36
     Capit
    0.36
     Stick
    0.36
     নৃত্য
    0.35
    ഴിഞ്ഞ
    0.35
    Activations Density 0.003%

    No Known Activations