© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2495
    Prev
    Next
    INDEX
    Explanations

    C/C++ code tokens related to source code file structure, image transformation matrices, MIME header parsing, and boolean expressions

    oai_token-act-pair · gemini-2.0-flash

    Code or definitions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ”)
    -0.59
    -)
    -0.57
    principalTable
    -0.57
    *)
    -0.57
    ）
    -0.56
    ’)
    -0.55
     *)
    -0.52
    )(-
    -0.52
    +)
    -0.52
    )
    -0.52
    POSITIVE LOGITS
    Obrázky
    0.63
    ReusableCell
    0.62
     ddelweddau
    0.61
    msgTypes
    0.60
     Мексичка
    0.58
    lardır
    0.55
    clearInterval
    0.54
     tartalomajánló
    0.54
     AspNetCore
    0.53
    posedge
    0.53
    Activations Density 5.645%

    No Known Activations