© 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. 173031
    Prev
    Next
    INDEX
    Explanations

    rahman, atman, brahman

    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
     پست
    0.56
    溸
    0.52
     ხელისუფლების
    0.52
     пост
    0.50
     gerakan
    0.50
     ವಿಚಾರ
    0.50
    خواندن
    0.50
     Bolshevik
    0.49
     فوټبال
    0.49
     მიმო
    0.48
    POSITIVE LOGITS
     for
    0.51
    for
    0.47
    을
    0.47
     have
    0.46
    ™
    0.46
    <0xF0>
    0.46
     за
    0.44
    히
    0.44
    위를
    0.44
     '
    0.43
    Activations Density 0.001%

    No Known Activations