© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11107
    Prev
    Next
    INDEX
    Explanations

    code snippets and formatting instructions, specifically regarding conditional statements

    oai_token-act-pair · gemini-2.0-flash

    programming 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_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     foramen
    -0.48
     gyvento
    -0.47
    허
    -0.46
     olsa
    -0.45
    knię
    -0.45
     benih
    -0.43
    tiously
    -0.43
    CharArray
    -0.42
     محفوظة
    -0.42
     NSCoder
    -0.42
    POSITIVE LOGITS
    tagHelperRunner
    0.90
     condition
    0.87
     Condition
    0.84
     CONDITION
    0.82
    condition
    0.81
    writeFieldEnd
    0.76
     conditions
    0.73
    Condition
    0.73
     CONDITIONS
    0.71
     fields
    0.68
    Activations Density 3.968%

    No Known Activations