© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3148
    Prev
    Next
    INDEX
    Explanations

    primary documents legislation

    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
     Zweifel
    0.37
    ெய்
    0.37
    㓶
    0.37
    投资基金
    0.37
    tape
    0.37
     срок
    0.37
     વચ્
    0.36
    creva
    0.36
    ასი
    0.36
    назна
    0.36
    POSITIVE LOGITS
     sim
    0.42
    祐
    0.41
     Brands
    0.41
    Docs
    0.41
    yness
    0.39
     Customers
    0.39
    Customers
    0.38
     Goliath
    0.38
     object
    0.37
     jus
    0.37
    Activations Density 0.030%

    No Known Activations