© 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. 10663
    Prev
    Next
    INDEX
    Explanations

    code, URLs, or specific entities

    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
     రామ
    0.39
    addEdge
    0.36
     Detected
    0.36
    arnos
    0.35
    vaal
    0.35
    庠
    0.35
    滞
    0.34
    द्व
    0.34
     Hawai
    0.33
    录
    0.33
    POSITIVE LOGITS
     ቤ
    0.41
    Cod
    0.39
    তি
    0.38
    Open
    0.37
    eight
    0.37
     Objective
    0.37
    emen
    0.36
    MEN
    0.36
     giddy
    0.36
    OBJ
    0.36
    Activations Density 0.053%

    No Known Activations