© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210141
    Prev
    Next
    INDEX
    Explanations

    lawfully or validly issued/arrested/obtained

    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_20_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
    assie
    0.44
    瓷
    0.42
    假设
    0.41
     Assume
    0.41
    ță
    0.40
    స్తున్న
    0.40
     seguenti
    0.40
     Luật
    0.40
    আমার
    0.39
    ujących
    0.39
    POSITIVE LOGITS
     conflict
    0.44
     vei
    0.44
    '_
    0.42
     ey
    0.41
     plaintext
    0.41
     '-'
    0.41
    Ott
    0.41
     exoner
    0.40
     couv
    0.40
    複数
    0.39
    Activations Density 0.001%

    No Known Activations