© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11195
    Prev
    Next
    INDEX
    Explanations

    SQL commands and related terms

    oai_token-act-pair · gemini-2.0-flash

    SQL queries

    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
    ⓘ
    -0.54
     pierdas
    -0.50
    доби
    -0.50
    OnLoad
    -0.49
    cardia
    -0.48
    SCAL
    -0.47
     Raceway
    -0.47
     dimo
    -0.46
     pula
    -0.43
     when
    -0.42
    POSITIVE LOGITS
    tagHelperRunner
    0.81
     Paglinawan
    0.81
    QMetaType
    0.79
     unknownFields
    0.73
    ThroughAttribute
    0.71
     defaultstate
    0.66
    IsMutable
    0.66
     pinulongan
    0.66
     doInBackground
    0.64
    GOTREF
    0.64
    Activations Density 5.895%

    No Known Activations