© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12462
    Prev
    Next
    INDEX
    Explanations

    text from US law

    oai_token-act-pair · gemini-2.0-flash

    words related to transportation or trucking

    np_token-act-pair-logits · gpt-4o-mini

    carrier

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    LookAnd
    -0.58
     engraçadas
    -0.55
    +#+#
    -0.49
    ongeza
    -0.48
    Blurb
    -0.48
    AntiForgeryToken
    -0.48
     Mitter
    -0.44
    تيجة
    -0.44
    drink
    -0.43
    Monster
    -0.43
    POSITIVE LOGITS
     carrier
    0.95
     carriers
    0.94
     Carriers
    0.80
     Carrier
    0.79
    carrier
    0.75
    Carrier
    0.73
     forward
    0.66
    Manbalar
    0.63
     StatefulWidget
    0.62
     Forward
    0.59
    Activations Density 1.907%

    No Known Activations