© 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. 14629
    Prev
    Next
    INDEX
    Explanations

    heart sounds

    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
    ከር
    0.59
     聞い
    0.58
    എം
    0.57
    渕
    0.57
    äden
    0.56
    ى
    0.56
    ман
    0.55
    ্ট
    0.55
    ൈ
    0.55
    aconda
    0.54
    POSITIVE LOGITS
    时间
    0.71
    u
    0.66
    0.63
    a
    0.62
     portugu
    0.61
     terse
    0.60
     algún
    0.60
     формирование
    0.60
     высо
    0.59
     energy
    0.59
    Activations Density 0.000%

    No Known Activations