© 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. 208432
    Prev
    Next
    INDEX
    Explanations

    numerical sequences and code checkpoints

    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
    да
    0.42
     प्रत्येक
    0.42
     each
    0.41
     pilota
    0.41
     fiecare
    0.40
     প্রশিক্ষ
    0.40
    ในการ
    0.40
    墘
    0.40
    工作
    0.39
     condo
    0.39
    POSITIVE LOGITS
    FindingsRequest
    0.44
     Could
    0.41
    tywn
    0.40
    ствовать
    0.39
     ተመሳሳይ
    0.39
     സംഭവ
    0.38
    ্টর
    0.38
    rya
    0.37
    ージュ
    0.37
    SendCommand
    0.37
    Activations Density 0.000%

    No Known Activations