© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5154
    Prev
    Next
    INDEX
    Explanations

    lines of code that are auto-generated and need to be completed

    oai_token-act-pair · gemini-2.0-flash

    auto-generated 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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Tikang
    -0.68
     للمعارف
    -0.67
    րջ
    -0.65
    govina
    -0.62
     esternos
    -0.61
    queryInterface
    -0.60
    MENAFN
    -0.59
    Tembelea
    -0.58
     المعيارى
    -0.58
    ఔ
    -0.57
    POSITIVE LOGITS
    AndEndTag
    0.57
    featureID
    0.57
     bronzo
    0.47
     "");
    0.47
    >();
    0.45
    "");
    0.44
     menek
    0.43
     debout
    0.42
    ")]
    0.42
    >");
    0.42
    Activations Density 0.983%

    No Known Activations