© 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-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12318
    Prev
    Next
    INDEX
    Explanations

    the names of universities and people in the context of academic achievements

    oai_token-act-pair · gemini-2.0-flash

    non-English language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DebuggerStep
    -0.73
     resourceCulture
    -0.66
    bootstrapcdn
    -0.65
    Jeografia
    -0.65
     שוליים
    -0.65
    Personendaten
    -0.61
    AccessorTable
    -0.61
    liceerd
    -0.57
     متعلقه
    -0.56
     بيها
    -0.55
    POSITIVE LOGITS
     Familienname
    0.50
    #+#
    0.49
     sagesse
    0.45
    برى
    0.44
     draught
    0.44
    HKEY
    0.43
    epiece
    0.43
    zepam
    0.43
     OSError
    0.42
     sàng
    0.42
    Activations Density 0.993%

    No Known Activations