© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7550
    Prev
    Next
    INDEX
    Explanations

    anonymous traffic routing

    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_40_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
    practical
    0.40
     practical
    0.39
    ొ
    0.38
     deb
    0.38
     advocate
    0.37
     DSF
    0.36
     scept
    0.35
    朼
    0.35
    sni
    0.35
     exchange
    0.35
    POSITIVE LOGITS
    azza
    0.51
     Rinse
    0.41
    ResultSet
    0.38
    asku
    0.38
    statusBar
    0.37
     maw
    0.37
    ześ
    0.36
    সংযোগ
    0.36
     Albert
    0.35
     Hallmark
    0.35
    Activations Density 0.039%

    No Known Activations