© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11976
    Prev
    Next
    INDEX
    Explanations

    proper nouns indicating places and positions of authority in Nigeria in Africa

    oai_token-act-pair · gemini-2.0-flash

    Countries

    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
    webElement
    -0.50
     nargin
    -0.46
     forstå
    -0.46
    ScopeManager
    -0.45
    expédition
    -0.43
     fleste
    -0.41
    MLLoader
    -0.41
     peruano
    -0.40
    ">${
    -0.40
     entender
    -0.40
    POSITIVE LOGITS
     HttpNotFound
    0.69
    OOTDTY
    0.66
    rawdę
    0.65
     CreateTagHelper
    0.64
     '\\;'
    0.63
    __(/*!
    0.62
    ImageContext
    0.61
    anthene
    0.59
    ыгана
    0.56
     мәкал
    0.55
    Activations Density 0.626%

    No Known Activations