© 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. 30913
    Prev
    Next
    INDEX
    Explanations

    local structure or minima

    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
    olc
    0.45
     boll
    0.41
     граф
    0.39
    Minecraft
    0.38
     Совет
    0.38
     波
    0.37
     ráp
    0.37
     فاض
    0.37
     неред
    0.37
    olite
    0.36
    POSITIVE LOGITS
    理想
    0.40
     hre
    0.39
    ヘ
    0.38
     Hessen
    0.38
     idéal
    0.38
    รอ
    0.36
     Ses
    0.35
    პ
    0.35
    nero
    0.35
     Heater
    0.35
    Activations Density 0.002%

    No Known Activations