© 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. 3084
    Prev
    Next
    INDEX
    Explanations

    python sys module

    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
    ために
    0.59
    <bos>
    0.57
    antaranya
    0.48
     sąd
    0.48
     adanya
    0.47
     ángulo
    0.47
    ための
    0.47
    y
    0.46
     можливість
    0.46
    angulo
    0.45
    POSITIVE LOGITS
    𝙣
    0.60
    𝙥
    0.51
    𝙨
    0.51
     gac
    0.50
    Σ
    0.49
    𝙙
    0.49
    𝙘
    0.49
     amic
    0.49
    𝙪
    0.49
     nomad
    0.48
    Activations Density 0.003%

    No Known Activations