© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    4. 124099
    Prev
    Next
    INDEX
    Explanations

    numerical measurements (cm, inches)

    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_37_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
     approximately
    0.52
     pribli
    0.51
     (+
    0.47
     приблизи
    0.47
     approx
    0.46
     Approximately
    0.46
    Approximately
    0.45
    约
    0.45
     aproximadamente
    0.44
     примерно
    0.44
    POSITIVE LOGITS
     Sod
    0.40
     Jeb
    0.38
    <$
    0.37
     ইরা
    0.37
     Dungeon
    0.37
     Apt
    0.36
    exch
    0.35
    ສ່ວນ
    0.35
     Gop
    0.34
     خواہش
    0.34
    Activations Density 0.001%

    No Known Activations