© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75029
    Prev
    Next
    INDEX
    Explanations

    learning and study time

    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_31_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
    )-$
    0.41
    jang
    0.40
     ceg
    0.37
    iaj
    0.36
     perpetuity
    0.35
     Mehta
    0.35
    JVM
    0.35
    虎
    0.35
    pImage
    0.35
     esboço
    0.34
    POSITIVE LOGITS
    மாகவும்
    0.40
     Pillow
    0.40
     dichiarato
    0.40
     Dest
    0.39
    规定的
    0.39
     DEL
    0.38
     enthält
    0.38
     Frost
    0.37
     моро
    0.37
    վ
    0.37
    Activations Density 0.000%

    No Known Activations