© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 241830
    Prev
    Next
    INDEX
    Explanations

    procedures followed by punctuation

    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
     दिशा
    0.43
     review
    0.42
     hold
    0.41
    双
    0.41
     command
    0.39
     двой
    0.38
    ը
    0.38
     dvoj
    0.38
    ॉ
    0.38
    },\\
    0.37
    POSITIVE LOGITS
     keuangan
    0.39
     coloquei
    0.39
    Teller
    0.38
    焓
    0.38
    शियों
    0.38
    িত্যক্ত
    0.37
    uyện
    0.37
     correr
    0.36
    liced
    0.36
    𝚏
    0.36
    Activations Density 0.002%

    No Known Activations