© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16024
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to waste management and recycling

    oai_token-act-pair · gemini-2.0-flash

    waste and recycling

    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
    <'
    -0.54
     skilful
    -0.53
     separations
    -0.52
     shit
    -0.50
    chnen
    -0.49
     circulaire
    -0.48
    Cpp
    -0.48
     separation
    -0.47
     SEPAR
    -0.47
    contentLoaded
    -0.47
    POSITIVE LOGITS
     SearchView
    0.62
    parsedMessage
    0.56
    atience
    0.55
     EClass
    0.55
    lesias
    0.54
     tartalomajánló
    0.53
    nasium
    0.50
    ंदीखरीदारी
    0.49
    kháu
    0.49
    licants
    0.49
    Activations Density 0.639%

    No Known Activations