© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6875
    Prev
    Next
    INDEX
    Explanations

    technical writing discussing malfunctions/problems and repair including but not limited to cars, batteries, and washing machines

    oai_token-act-pair · gemini-2.0-flash

    mechanical or technical failures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     AssemblyCulture
    -1.01
     Paglinawan
    -0.66
    piram
    -0.64
    HasAnnotation
    -0.63
    DataAnnotations
    -0.60
     mergeFrom
    -0.60
     بيها
    -0.58
    ("'"
    -0.58
     تضيفلها
    -0.57
    fillType
    -0.56
    POSITIVE LOGITS
    localctx
    0.63
     over
    0.55
    protoc
    0.53
    over
    0.48
    Over
    0.47
    Appellants
    0.47
    findpost
    0.45
     softened
    0.44
     Liquid
    0.44
     ControllerBase
    0.43
    Activations Density 3.994%

    No Known Activations