© 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. 13921
    Prev
    Next
    INDEX
    Explanations

    dopamine release

    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
     Ирина
    0.45
    甜
    0.45
    дом
    0.44
    Times
    0.43
    Fang
    0.43
    峰
    0.43
    語
    0.42
    सम्म
    0.41
    Thom
    0.41
    记
    0.40
    POSITIVE LOGITS
    }//
    0.48
     সীমান্তে
    0.45
    holung
    0.44
    t
    0.44
    alloway
    0.43
    豺
    0.43
    urato
    0.43
     downloader
    0.42
     entitles
    0.42
    };
    0.42
    Activations Density 0.038%

    No Known Activations