© 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. 10516
    Prev
    Next
    INDEX
    Explanations

    United Nations projections

    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
    Trailer
    0.37
     هە
    0.36
    汗
    0.36
    Modular
    0.34
    NumberOperation
    0.34
    ,"%
    0.33
    Perry
    0.33
     usur
    0.33
    Operand
    0.33
    Mint
    0.33
    POSITIVE LOGITS
     чы
    0.37
    িয়ন
    0.37
    ークル
    0.37
    𝒑
    0.37
     আদেশ
    0.36
    crom
    0.36
     BOC
    0.35
     GCP
    0.35
     Mr
    0.35
    eof
    0.35
    Activations Density 0.000%

    No Known Activations