© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 195737
    Prev
    Next
    INDEX
    Explanations

    fraction arithmetic

    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_26_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
    軋
    0.35
     اعتبار
    0.35
    마다
    0.34
     abroad
    0.33
     машиналары
    0.33
    Sof
    0.33
     chau
    0.33
    蓥
    0.33
    ضل
    0.32
     आदी
    0.32
    POSITIVE LOGITS
     problém
    0.37
     ARCH
    0.34
    archy
    0.33
     devemos
    0.33
     поч
    0.33
     disastrous
    0.33
    ্রী
    0.32
     necessário
    0.32
     rebus
    0.32
     zebrafish
    0.32
    Activations Density 0.002%

    No Known Activations