© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 203887
    Prev
    Next
    INDEX
    Explanations

    ventricular fibrillation

    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_37_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
     ચૂ
    0.38
     unborn
    0.37
     fireman
    0.37
     бя
    0.36
     смерти
    0.36
    Ꮳ
    0.36
    green
    0.35
    :%
    0.35
    በባ
    0.35
    جمالي
    0.35
    POSITIVE LOGITS
     prepared
    0.41
     contemplative
    0.39
     getDefault
    0.39
     tav
    0.38
     contemplates
    0.38
     Violin
    0.38
     VIDA
    0.38
    prepare
    0.37
     cell
    0.37
    ❞
    0.37
    Activations Density 0.002%

    No Known Activations