© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12642
    Prev
    Next
    INDEX
    Explanations

    the prefix "geo" and the word "geonomics"

    oai_token-act-pair · gemini-2.0-flash

    geonomics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    pearing
    -0.59
    Istorija
    -0.55
    \|^{
    -0.49
    ResponseEntity
    -0.47
     effet
    -0.47
    stolic
    -0.47
    omethane
    -0.46
    تمع
    -0.46
    nel
    -0.46
    efeller
    -0.46
    POSITIVE LOGITS
     CWE
    0.50
    ModelAdmin
    0.47
    \{\\
    0.47
     Châ
    0.47
    __(/*!
    0.47
    ย์
    0.45
     tombé
    0.43
     azy
    0.43
    KommentareTeilen
    0.42
     obrazov
    0.42
    Activations Density 0.213%

    No Known Activations