© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89627
    Prev
    Next
    INDEX
    Explanations

    pathogenic, atherogenic, pyogenic

    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_3_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
    A
    0.78
    Му
    0.64
    4
    0.63
    a
    0.62
     가서
    0.61
    J
    0.60
    I
    0.59
     latach
    0.59
     protégé
    0.59
     갔
    0.59
    POSITIVE LOGITS
    of
    0.72
    ю
    0.58
    чие
    0.58
    дят
    0.58
    ين
    0.57
    culaire
    0.56
     Verkehrs
    0.56
    ERRY
    0.55
    ккей
    0.54
    িত্তিক
    0.53
    Activations Density 0.000%

    No Known Activations