© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15544
    Prev
    Next
    INDEX
    Explanations

    German sentences related to writing letters and grammar

    oai_token-act-pair · gemini-2.0-flash

    Foreign 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_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
     betweenstory
    -0.52
    IsPostBack
    -0.50
    SourceChecksum
    -0.50
    propTypes
    -0.46
    readAs
    -0.45
     <=",
    -0.45
    FORME
    -0.45
     jsPsych
    -0.44
    AddTagHelper
    -0.43
    مصادر
    -0.43
    POSITIVE LOGITS
    Vidite
    0.75
     Chwiliwch
    0.69
    ConverterFactory
    0.66
    ArgsConstructor
    0.64
     CreateTagHelper
    0.59
     Shakspeare
    0.54
    Tikang
    0.52
    évaluateur
    0.50
     contigo
    0.49
     JTable
    0.49
    Activations Density 0.554%

    No Known Activations