© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137858
    Prev
    Next
    INDEX
    Explanations

    marker following punctuation or separators

    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_12_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
    <0x80>
    0.51
    ى
    0.50
    йся
    0.49
     estudos
    0.48
    ческими
    0.47
    ენტის
    0.46
    цтва
    0.46
     नव्ह
    0.45
    енти
    0.44
    кован
    0.44
    POSITIVE LOGITS
    Lora
    0.53
     Cellulose
    0.53
    T
    0.50
     Lisbon
    0.49
     Parmesan
    0.48
     housewives
    0.48
     Patty
    0.47
     பட்
    0.47
    Pat
    0.46
    ཤ
    0.46
    Activations Density 0.001%

    No Known Activations