© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5468
    Prev
    Next
    INDEX
    Explanations

    words related to the progress, path, extent, or state of something, or its true essence.

    oai_token-act-pair · gemini-2.0-flash

    course

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.74
    '
    -0.67
     dignité
    -0.62
     maș
    -0.58
     hendes
    -0.56
    ↵↵
    -0.55
     spéciaux
    -0.54
     librement
    -0.54
     sonno
    -0.54
     pauvres
    -0.53
    POSITIVE LOGITS
    AddTagHelper
    0.96
     ligiloj
    0.93
    tvguidetime
    0.90
     CreateTagHelper
    0.89
    interopRequire
    0.87
     EconPapers
    0.86
    Jeografia
    0.85
     intptr
    0.85
    pertino
    0.84
     saites
    0.82
    Activations Density 1.783%

    No Known Activations