© 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-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51947
    Prev
    Next
    INDEX
    Explanations

    son of God or Timothy

    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_30_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
    赝
    0.37
     ცხ
    0.36
    вовано
    0.35
     люби
    0.35
    痩
    0.34
    یده
    0.34
     როგორ
    0.33
    㑯
    0.33
     brute
    0.33
    гада
    0.32
    POSITIVE LOGITS
     डालेंगे
    0.38
     stitch
    0.38
    atching
    0.37
     Ert
    0.37
     মামুন
    0.36
     Middlesbrough
    0.35
     wool
    0.35
     деталей
    0.35
    discrimin
    0.35
     Dunedin
    0.34
    Activations Density 0.000%

    No Known Activations