© 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. 5920
    Prev
    Next
    INDEX
    Explanations

    references to committees

    oai_token-act-pair · gemini-2.0-flash

    committee

    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
    Autoritní
    -0.84
    Fordítás
    -0.84
    bibfield
    -0.75
    bibinfo
    -0.73
    veien
    -0.69
    BibitemShut
    -0.68
    hæng
    -0.67
    daß
    -0.66
    wijze
    -0.65
     actual
    -0.63
    POSITIVE LOGITS
     riuscito
    0.80
     Lign
    0.78
    “
    0.75
     AssemblyProduct
    0.75
    <strong>
    0.73
     dolomite
    0.70
     brinquedo
    0.68
     dimentic
    0.68
     Tripod
    0.67
     néglig
    0.67
    Activations Density 2.035%

    No Known Activations