© 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. 13401
    Prev
    Next
    INDEX
    Explanations

    name/names

    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
    ＆
    0.41
    ograv
    0.37
    또한
    0.35
    onter
    0.34
    م
    0.34
    てください
    0.33
     பரிசு
    0.33
    ttle
    0.33
    ster
    0.32
    erer
    0.32
    POSITIVE LOGITS
     agricultura
    0.49
     l
    0.42
     externa
    0.40
     Baltic
    0.40
    体育
    0.39
     datos
    0.39
    -',
    0.38
     estrada
    0.38
     agricult
    0.38
     agri
    0.38
    Activations Density 0.058%

    No Known Activations