© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9944
    Prev
    Next
    INDEX
    Explanations

    probability P( |

    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_13_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
    را
    0.11
    "，
    0.11
    ίκ
    0.11
    καν
    0.11
    ί
    0.11
    نا
    0.11
    OPA
    0.10
    %，
    0.10
    Morgan
    0.10
    ன்
    0.10
    POSITIVE LOGITS
    ৭
    0.14
     Psychiatry
    0.12
    ベント
    0.12
     acclaimed
    0.12
     expel
    0.12
     minifyEnabled
    0.12
     Benim
    0.12
     sklep
    0.12
     Lietuvos
    0.12
     Paribas
    0.12
    Activations Density 0.029%

    No Known Activations