© 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. 2227
    Prev
    Next
    INDEX
    Explanations

    french text with some english place names

    oai_token-act-pair · gemini-2.0-flash

    programming terminology or language constructs

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

    Canada related texts

    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
     estekak
    -0.68
    ագրություններ
    -0.64
    addCriterion
    -0.64
    NewUrlParser
    -0.59
    发表于
    -0.59
    
    -0.57
    TypedDataSet
    -0.57
    toBeTruthy
    -0.57
     Ephe
    -0.55
     easel
    -0.53
    POSITIVE LOGITS
    okat
    0.54
    xun
    0.48
    etcode
    0.48
    letus
    0.48
    ultati
    0.47
     üzere
    0.46
    didSet
    0.45
     demografica
    0.45
     US
    0.44
    loyd
    0.44
    Activations Density 1.664%

    No Known Activations