© 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. 660
    Prev
    Next
    INDEX
    Explanations

    DD-WRT, DDTS, Ditto

    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
     useState
    0.43
    িত
    0.42
    燉
    0.38
     फेल
    0.38
     Havel
    0.37
    沆
    0.37
    Cancelled
    0.37
    棻
    0.36
    犢
    0.36
     प्रदेश
    0.36
    POSITIVE LOGITS
    house
    0.46
     competit
    0.41
    head
    0.40
    competition
    0.39
     competition
    0.39
     compét
    0.39
    compet
    0.38
    count
    0.38
     house
    0.38
    opro
    0.38
    Activations Density 0.016%

    No Known Activations