© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4918
    Prev
    Next
    INDEX
    Explanations

    the word "fine" in different contexts, sometimes related to tuning or adjustments, and sometimes alongside other words like "dry" or "safe"

    oai_token-act-pair · gemini-2.0-flash

    fine

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    ViewImports
    -0.86
    ContentLoaded
    -0.78
     AssemblyCompany
    -0.65
     مرئيه
    -0.65
     quæ
    -0.64
    abestanden
    -0.64
    +#+#
    -0.62
     ostavi
    -0.59
     indisponible
    -0.56
    photobucket
    -0.52
    POSITIVE LOGITS
    thâu
    0.55
    engo
    0.53
    aute
    0.52
    SuspendLayout
    0.51
    Nimbus
    0.50
    tinyos
    0.50
    wikimedia
    0.49
    prnewswire
    0.49
    ulex
    0.48
    NameInMap
    0.48
    Activations Density 8.646%

    No Known Activations