© 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. 2469
    Prev
    Next
    INDEX
    Explanations

    franz beckenbauer

    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
     द्वीप
    0.48
    DebugInformation
    0.42
     IPL
    0.41
    IPL
    0.40
    ியார்
    0.39
    岛
    0.38
     "{{
    0.38
     ISLAND
    0.38
    繭
    0.37
     नल
    0.36
    POSITIVE LOGITS
    дагы
    0.40
     dxc
    0.38
     टक्के
    0.37
    лян
    0.36
    нова
    0.36
     confl
    0.36
    苅
    0.36
    queda
    0.35
     trekk
    0.35
    MT
    0.35
    Activations Density 0.014%

    No Known Activations