© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 154833
    Prev
    Next
    INDEX
    Explanations

    close

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    ançaise
    0.41
    ♏
    0.39
    due
    0.37
    乐观
    0.37
     ناح
    0.36
    NESOTA
    0.36
    ό
    0.36
     Nasser
    0.35
     Ă
    0.35
     ka
    0.35
    POSITIVE LOGITS
    Acute
    0.40
    Jeffrey
    0.39
     引き
    0.37
     ओळख
    0.37
    বিস্ত
    0.37
     ಇಲ್ಲಿ
    0.37
    囝
    0.37
    Gü
    0.37
    玻
    0.37
    घो
    0.36
    Activations Density 0.000%

    No Known Activations