© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4788
    Prev
    Next
    INDEX
    Explanations

    words in Croatian related to Facebook accounts, phone numbers, and email addresses

    oai_token-act-pair · gemini-2.0-flash

    Croatian Facebook messages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    BeginContext
    -0.60
    DoubleQuotes
    -0.59
    FTFY
    -0.59
    XmlAccessType
    -0.57
     cherchés
    -0.53
    InstanceState
    -0.52
     кӀош
    -0.52
    :]:
    -0.52
     Púb
    -0.51
    ثيق
    -0.50
    POSITIVE LOGITS
    ########.
    0.82
    SharedCtor
    0.69
    <bos>
    0.65
     resourceCulture
    0.56
    mes
    0.52
    FileVersion
    0.52
    flex
    0.48
     LIBR
    0.47
     Pils
    0.47
     coronavirus
    0.45
    Activations Density 5.094%

    No Known Activations