© 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. 9899
    Prev
    Next
    INDEX
    Explanations

    `def` followed by module or bib definitions

    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
    ريع
    0.39
     adjusts
    0.38
    出手
    0.37
    근
    0.37
     efficiency
    0.37
     Petersburg
    0.37
     certificate
    0.37
     digs
    0.37
    ongi
    0.36
    aliy
    0.36
    POSITIVE LOGITS
    OTAL
    0.40
    ùm
    0.39
     indígena
    0.38
     hardworking
    0.38
    Indigenous
    0.38
    𝗝
    0.36
    റ്റ്
    0.36
    MDET
    0.36
    dden
    0.35
    च्च
    0.35
    Activations Density 0.000%

    No Known Activations