© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7519
    Prev
    Next
    INDEX
    Explanations

    all-caps acronyms and abbreviations

    oai_token-act-pair · gemini-2.0-flash

    unusual or obscure terms

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

    Code syntax

    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
     je
    -0.46
     d
    -0.35
     ja
    -0.34
     da
    -0.33
     e
    -0.32
    odal
    -0.32
     une
    -0.31
     se
    -0.30
    consulté
    -0.30
     die
    -0.30
    POSITIVE LOGITS
     myſelf
    1.16
     itſelf
    1.16
    
    1.02
     ſeveral
    1.02
     Monfieur
    1.00
     fevere
    1.00
     photolibrary
    0.96
     Jefus
    0.96
    ^(@)
    0.96
     ſever
    0.95
    Activations Density 2.492%

    No Known Activations