© 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. 8283
    Prev
    Next
    INDEX
    Explanations

    discourse markers and quantifiers

    oai_token-act-pair · gemini-2.0-flash

    there

    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
    անդ
    -0.50
    having
    -0.47
     having
    -0.45
    createServer
    -0.43
    buh
    -0.43
     москве
    -0.43
    子和
    -0.42
    أما
    -0.41
    Specifiche
    -0.41
     ovat
    -0.41
    POSITIVE LOGITS
     there
    2.42
    there
    1.89
     There
    1.81
     THERE
    1.77
    There
    1.73
    THERE
    1.53
     هناك
    1.36
     theres
    1.22
     thither
    1.16
    theres
    1.12
    Activations Density 2.248%

    No Known Activations