© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 12227
    Prev
    Next
    INDEX
    Explanations

    loss of momentum

    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
    mushroom
    0.39
    hour
    0.38
     محاضره
    0.38
    oggle
    0.36
     دولة
    0.36
    \
    0.36
    λούν
    0.35
    getAction
    0.35
    &
    0.35
     محاضرت
    0.35
    POSITIVE LOGITS
     Fife
    0.41
     it
    0.37
     п
    0.37
     p
    0.36
     Estes
    0.35
     h
    0.35
     FMT
    0.34
    c
    0.34
     Cyg
    0.33
     cim
    0.33
    Activations Density 0.040%

    No Known Activations