© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 215137
    Prev
    Next
    INDEX
    Explanations

    places and websites

    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_50_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
     Kays
    0.49
     shel
    0.49
     Kom
    0.43
    Mer
    0.43
    Kont
    0.43
    Э
    0.43
     thee
    0.42
     bootstra
    0.42
     juntas
    0.42
     W
    0.42
    POSITIVE LOGITS
    habitude
    0.42
    শ্বরের
    0.37
    ogloss
    0.37
    ilitar
    0.36
    urgiu
    0.36
    ாள
    0.36
    Invocation
    0.36
    ală
    0.35
    sendBuf
    0.35
     হাব
    0.34
    Activations Density 0.001%

    No Known Activations