© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15855
    Prev
    Next
    INDEX
    Explanations

    German text about writing or constructing sentences with multiple verbs

    oai_token-act-pair · gemini-2.0-flash

    foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    TagMode
    -0.70
    aarrggbb
    -0.60
     متعلقه
    -0.58
    PreferredItem
    -0.57
    webElementXpaths
    -0.55
     autorytatywna
    -0.55
     felicità
    -0.52
    ChromeDriver
    -0.52
     esternos
    -0.52
     betweenstory
    -0.51
    POSITIVE LOGITS
     mit
    0.53
    feira
    0.52
    Mit
    0.50
     Mit
    0.50
     det
    0.49
    kháu
    0.49
    Das
    0.48
    %</
    0.48
    BitConverter
    0.48
     Das
    0.47
    Activations Density 4.627%

    No Known Activations