© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 150475
    Prev
    Next
    INDEX
    Explanations

    intensity or emotion

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     людей
    0.38
    知识
    0.38
     appareil
    0.37
    չ
    0.37
    知識
    0.37
     appareils
    0.37
    intl
    0.36
    });
    0.34
    poi
    0.34
    accounting
    0.34
    POSITIVE LOGITS
     very
    0.64
     дуже
    0.56
     dream
    0.53
     molto
    0.51
     очень
    0.50
     rất
    0.50
     muy
    0.49
     bardzo
    0.49
     sehr
    0.49
     Very
    0.49
    Activations Density 0.007%

    No Known Activations