© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5482
    Prev
    Next
    INDEX
    Explanations

    LaTeX code

    oai_token-act-pair · gemini-2.0-flash

    delimiters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     AttributeSet
    -0.61
     stage
    -0.49
    agger
    -0.49
     Spice
    -0.49
    usermodel
    -0.48
    thâu
    -0.47
     Force
    -0.47
    μισ
    -0.46
     Overflow
    -0.46
     force
    -0.45
    POSITIVE LOGITS
     akik
    0.62
    tinyos
    0.60
     feroit
    0.57
    endphp
    0.57
     tartalomajánló
    0.57
    StructEnd
    0.56
    Gön
    0.55
    tagHelperRunner
    0.55
    FunctionFlags
    0.54
    ferrer
    0.54
    Activations Density 2.014%

    No Known Activations