© 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
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 91070
    Prev
    Next
    INDEX
    Explanations

    G

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    mipmap
    0.43
    tensorflow
    0.40
    collectionView
    0.40
    𝐨
    0.40
     سننے
    0.39
    bokeh
    0.39
    obu
    0.38
    haman
    0.38
    rith
    0.37
    ack
    0.37
    POSITIVE LOGITS
     NOW
    0.48
     ahora
    0.47
     U
    0.44
     Rocket
    0.44
     Post
    0.43
     Now
    0.42
     now
    0.41
     నగ
    0.40
     sekarang
    0.40
     Study
    0.40
    Activations Density 0.000%

    No Known Activations