© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53847
    Prev
    Next
    INDEX
    Explanations

    action or consequence following 'so'

    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_31_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
    砒
    0.39
     বৈ
    0.37
    なので
    0.36
     geos
    0.35
     Ahí
    0.35
     kuba
    0.35
     joten
    0.35
    児
    0.34
     Deshalb
    0.34
    だったので
    0.33
    POSITIVE LOGITS
    ғ
    0.39
     comfort
    0.37
     excepciones
    0.36
    exceptions
    0.36
     quickest
    0.35
     خریداری
    0.34
    absorbing
    0.34
    comfort
    0.34
     comodidad
    0.33
     সন্ধ্যায়
    0.33
    Activations Density 0.003%

    No Known Activations