© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5910
    Prev
    Next
    INDEX
    Explanations

    words or phrases associated with online forms, user feedback, or requests

    oai_token-act-pair · gemini-2.0-flash

    User comments and feedback

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     hearing
    -0.77
     heard
    -0.76
     hear
    -0.73
     hears
    -0.73
    hear
    -0.73
     listening
    -0.71
    Hear
    -0.71
     listened
    -0.68
     Hear
    -0.67
     escu
    -0.65
    POSITIVE LOGITS
    \{\\
    0.71
    المشاركات
    0.69
     contacting
    0.69
    Comentários
    0.67
     Photocase
    0.66
     criticise
    0.63
    SerializedSize
    0.63
    IntoConstraints
    0.62
    verwijspagina
    0.60
    цездатний
    0.60
    Activations Density 2.091%

    No Known Activations