© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12514
    Prev
    Next
    INDEX
    Explanations

    words and phrases that begin subjective clauses, or clauses that refer to the writer

    oai_token-act-pair · gemini-2.0-flash

    what

    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
    tahui
    -0.49
    вік
    -0.46
    หมือน
    -0.46
    XmlAccessType
    -0.46
    +#+
    -0.46
    alors
    -0.45
    testcase
    -0.44
    mez
    -0.42
    poved
    -0.42
    reach
    -0.42
    POSITIVE LOGITS
    OGND
    0.74
     Италијани
    0.60
    ThroughAttribute
    0.60
    BeginContext
    0.59
    endregion
    0.59
     actionTypes
    0.57
     Roskov
    0.57
    rovnik
    0.55
    AndEndTag
    0.54
    ":[{
    0.54
    Activations Density 1.362%

    No Known Activations