© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1531
    Prev
    Next
    INDEX
    Explanations

    words that are references to logic, academia, scientific studies, or commentary.

    oai_token-act-pair · gemini-2.0-flash

    political/social discourse

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     kaupung
    -0.40
    NullException
    -0.39
     femininos
    -0.37
     fieltro
    -0.36
     näky
    -0.36
     uitges
    -0.35
     desglose
    -0.34
     avulla
    -0.34
     oluşan
    -0.33
    liğ
    -0.33
    POSITIVE LOGITS
     hammer
    0.96
     wheels
    0.96
     wheel
    0.93
     dust
    0.92
     guns
    0.91
     curtains
    0.86
    GEBURTSDATUM
    0.86
     smoke
    0.85
     rope
    0.84
     sails
    0.84
    Activations Density 8.717%

    No Known Activations