© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79543
    Prev
    Next
    INDEX
    Explanations

    levothyroxine, matrilineal

    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_0_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
    (
    1.40
     and
    1.38
    geving
    1.27
     fuer
    1.27
     сделали
    1.22
    dienst
    1.21
    dine
    1.20
     zei
    1.18
     onder
    1.16
     سي
    1.13
    POSITIVE LOGITS
    ا
    2.19
    在
    2.16
    一
    2.06
    も
    1.91
    ру
    1.89
    도
    1.79
    ш
    1.70
    ה
    1.62
    мі
    1.60
    ش
    1.59
    Activations Density 0.000%

    No Known Activations