© 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. 5135
    Prev
    Next
    INDEX
    Explanations

    place or area names, especially French regions or départements

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    setVerticalGroup
    -0.58
    llllll
    -0.49
    ıldığı
    -0.48
    quine
    -0.48
    jsonwebtoken
    -0.47
    othelioma
    -0.47
    жнарод
    -0.46
     Carp
    -0.46
     berea
    -0.46
    peted
    -0.44
    POSITIVE LOGITS
     AssemblyTitle
    0.66
    Попис
    0.60
     незавершена
    0.57
     AssemblyCulture
    0.54
    Filmografie
    0.52
    +#+#
    0.50
     Exacts
    0.48
    (&:
    0.48
    #+#
    0.48
    <()>
    0.47
    Activations Density 9.250%

    No Known Activations