© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12536
    Prev
    Next
    INDEX
    Explanations

    code and numerical mathematical symbols

    oai_token-act-pair · gemini-2.0-flash

    Code snippets and URLs

    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
     faj
    -0.45
     Kini
    -0.42
     soba
    -0.40
     buta
    -0.40
     SOB
    -0.39
    حياته
    -0.39
     SSN
    -0.39
    ㎠
    -0.39
     IMC
    -0.39
     bhi
    -0.39
    POSITIVE LOGITS
     חיצוניים
    0.57
     맞
    0.57
    랬
    0.56
     될
    0.54
     간
    0.54
     집
    0.52
     군
    0.52
     노
    0.52
     살
    0.52
    대로
    0.52
    Activations Density 4.690%

    No Known Activations