© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5832
    Prev
    Next
    INDEX
    Explanations

    sentences about fines from the European Commission

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     jsPsych
    -0.79
     ProtoMessage
    -0.76
    UnsafeEnabled
    -0.73
     Roskov
    -0.69
    رشف
    -0.68
    XmlAccessType
    -0.68
     Theſe
    -0.66
     مشين
    -0.66
     Италијани
    -0.66
    enderror
    -0.65
    POSITIVE LOGITS
    صدار
    0.47
    itivo
    0.47
     Fick
    0.46
    ώρα
    0.45
    뜻
    0.45
     Guille
    0.45
    ik
    0.44
    produ
    0.44
     faute
    0.44
     querer
    0.44
    Activations Density 6.966%

    No Known Activations