© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85561
    Prev
    Next
    INDEX
    Explanations

    specific software names and entities

    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_3_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
     ನಾನು
    0.70
    ه
    0.69
    ER
    0.64
    ේ
    0.64
    ać
    0.63
     doorbell
    0.62
     stewardship
    0.61
     dimer
    0.60
     കൂടുതല്‍
    0.60
     cleanest
    0.60
    POSITIVE LOGITS
    x
    0.92
    คุณ
    0.69
    h
    0.67
    v
    0.66
    й
    0.63
     wenige
    0.63
    غ
    0.59
    ఖ్య
    0.59
     irgend
    0.59
    一片
    0.59
    Activations Density 0.008%

    No Known Activations