© 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-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3190
    Prev
    Next
    INDEX
    Explanations

    technical keywords like equation, DSA, Strange

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
    ن
    0.88
    не
    0.79
    ন
    0.78
    на
    0.78
    oz
    0.76
    eria
    0.73
    ρού
    0.72
    ])
    0.71
     kett
    0.70
    nej
    0.69
    POSITIVE LOGITS
    ່
    0.85
     квітня
    0.82
     nominating
    0.82
     lumped
    0.81
    क्शन
    0.81
    ᱾
    0.80
    switching
    0.80
    <unused0>
    0.80
    驁
    0.80
     लिख
    0.79
    Activations Density 0.001%

    No Known Activations