© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195316
    Prev
    Next
    INDEX
    Explanations

    strong feelings, emotions, and connotations

    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_15_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
    Ка
    0.58
    吟
    0.55
    ihal
    0.54
    리소스
    0.52
     پھ
    0.51
     échanc
    0.51
    На
    0.50
    まつ
    0.50
    糍
    0.50
    ಿಕೊಂಡು
    0.50
    POSITIVE LOGITS
    xiety
    0.60
    te
    0.59
     Pre
    0.52
     te
    0.51
    orry
    0.51
     Te
    0.50
    um
    0.50
     Dyer
    0.49
    ere
    0.48
    zy
    0.48
    Activations Density 0.010%

    No Known Activations