© 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. 12928
    Prev
    Next
    INDEX
    Explanations

    words related to money and payment

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
     StringTokenizer
    -0.69
    stdc
    -0.68
     InputDecoration
    -0.65
    cipy
    -0.63
    SourceChecksum
    -0.62
     pleaſure
    -0.62
    tagHelper
    -0.62
     placental
    -0.61
    יצוני
    -0.61
    webElementXpaths
    -0.60
    POSITIVE LOGITS
     Chwiliwch
    0.62
    省市镇
    0.50
     quelles
    0.46
     boîtes
    0.45
    TO
    0.45
     Lightboxes
    0.44
     quels
    0.40
    dehydes
    0.40
    md
    0.39
    を経
    0.39
    Activations Density 0.828%

    No Known Activations