© 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. 12326
    Prev
    Next
    INDEX
    Explanations

    somewhat nonsensical phrases related to a supernatural battle involving breaking, bursting, fairy kings, and holy items

    oai_token-act-pair · gemini-2.0-flash

    movement/change

    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
    XmlAccessType
    -0.67
    BeginContext
    -0.66
    новништво
    -0.65
     useDispatch
    -0.64
     препратки
    -0.63
     linkovi
    -0.60
    UpInside
    -0.60
    PerformLayout
    -0.60
    IVEREF
    -0.59
    ケート
    -0.58
    POSITIVE LOGITS
     ihop
    0.43
    glä
    0.42
    omer
    0.40
    outs
    0.40
    NewUrlParser
    0.39
    執
    0.39
    CreateModel
    0.38
    ządu
    0.38
    out
    0.37
    ticides
    0.37
    Activations Density 0.721%

    No Known Activations