© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10727
    Prev
    Next
    INDEX
    Explanations

    a variety of technical, legal, and sports-related terms and references.

    oai_token-act-pair · gemini-2.0-flash

    legal citations

    np_max-act · gemini-2.0-flash

    three

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     PWN
    -0.65
    存于互联网档案馆
    -0.65
    RenderAtEndOf
    -0.62
    FailureListener
    -0.61
    jsonwebtoken
    -0.60
     Völker
    -0.60
    Johnston
    -0.59
    Signer
    -0.59
    usermodel
    -0.59
    lahoma
    -0.58
    POSITIVE LOGITS
    3
    1.23
    THREE
    1.05
     THREE
    1.05
     Three
    1.02
     trio
    1.02
     three
    0.99
     III
    0.97
    rd
    0.96
    .³
    0.96
    three
    0.95
    Activations Density 8.396%

    No Known Activations