© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10121
    Prev
    Next
    INDEX
    Explanations

    the word "wind", especially in the context of energy or weather

    oai_token-act-pair · gemini-2.0-flash

    wind

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Phono
    -0.69
     ComVisible
    -0.67
     gesta
    -0.65
    #+#
    -0.64
     ankles
    -0.63
    archiviato
    -0.63
     Catho
    -0.60
    ufact
    -0.59
     photolibrary
    -0.59
    URLException
    -0.58
    POSITIVE LOGITS
    évaluateur
    0.50
    AddHtmlAttribute
    0.46
    бият
    0.44
    pust
    0.44
    canActivate
    0.43
    DoubleQuotes
    0.42
    featureID
    0.42
    Kanpo
    0.39
    Skocz
    0.39
    eliner
    0.38
    Activations Density 0.705%

    No Known Activations