© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 200260
    Prev
    Next
    INDEX
    Explanations

    f followed by 4

    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
    Negative Logits
    नामेंट
    0.45
    rakk
    0.45
    uzzy
    0.39
    mole
    0.37
    openai
    0.37
     ####
    0.37
     Shout
    0.37
     Monopoly
    0.37
    GPT
    0.36
     Pancakes
    0.36
    POSITIVE LOGITS
    DataSet
    0.45
    ्‍
    0.42
     вследствие
    0.41
     appreciable
    0.40
    providecommand
    0.39
     разнови
    0.39
     abund
    0.38
     ascertaining
    0.36
    Gar
    0.36
     humankind
    0.36
    Activations Density 0.009%

    No Known Activations