© 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. 7948
    Prev
    Next
    INDEX
    Explanations

    Final Answer/thought structure

    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
     bescherm
    0.38
    ｂ
    0.38
    ปก
    0.37
     sphincter
    0.37
     benzoate
    0.37
     buz
    0.36
    ielten
    0.36
    hma
    0.36
    ινή
    0.35
     flu
    0.35
    POSITIVE LOGITS
     potencial
    0.46
    쿱
    0.38
     Dodge
    0.37
    тити
    0.37
     potenciales
    0.37
     potens
    0.37
     comunidades
    0.36
    拉斯
    0.36
    ^^
    0.35
    Utilization
    0.35
    Activations Density 0.014%

    No Known Activations