© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120494
    Prev
    Next
    INDEX
    Explanations

    binary search code

    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_27_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
    கிழ
    0.41
    🌼
    0.37
    返す
    0.36
    лите
    0.36
    লিখ
    0.35
     数字
    0.35
    Computed
    0.35
     exuber
    0.35
    换
    0.35
    звичай
    0.35
    POSITIVE LOGITS
     Astrology
    0.41
     Spirits
    0.38
     Genomics
    0.38
     Clothing
    0.38
     ચા
    0.37
     Talks
    0.37
     Teaching
    0.37
    ajuan
    0.36
     Psychic
    0.36
    
    0.36
    Activations Density 0.000%

    No Known Activations