© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 139566
    Prev
    Next
    INDEX
    Explanations

    base course

    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
    </h3>
    0.19
     astrophys
    0.18
    '
    0.18
    ри
    0.18
     Atomic
    0.18
     novels
    0.17
    el
    0.17
     Table
    0.17
     MILLER
    0.17
     base
    0.17
    POSITIVE LOGITS
    ЕНИЕ
    0.19
     现在
    0.18
    7
    0.17
     약
    0.17
    一眼
    0.17
    方に
    0.17
     जलन
    0.17
     યોજના
    0.17
    स्टाइल
    0.16
     tasmim
    0.16
    Activations Density 0.009%

    No Known Activations