© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8411
    Prev
    Next
    INDEX
    Explanations

    words related to oral health

    oai_token-act-pair · gemini-2.0-flash

    terms related to saliva and mouth functions

    np_token-act-pair-logits · gpt-4o-mini

    tongue and language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     transférez
    -0.69
    theless
    -0.66
    %");
    -0.57
    setCellStyle
    -0.57
     autorytatywna
    -0.55
    baskets
    -0.55
     Efq
    -0.55
    iseries
    -0.54
    expandindo
    -0.54
     initComponents
    -0.53
    POSITIVE LOGITS
     lengua
    0.65
     language
    0.64
     tongue
    0.63
     tongues
    0.63
     língua
    0.60
     lingua
    0.58
     languages
    0.57
     spit
    0.56
     speaking
    0.56
    sub
    0.55
    Activations Density 1.972%

    No Known Activations