© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10666
    Prev
    Next
    INDEX
    Explanations

    code related to Python import statements, especially those that fail

    oai_token-act-pair · gemini-2.0-flash

    technical terms and identifiers

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

    Code and programming

    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
    stateMutability
    -0.63
    lusst
    -0.59
    ModelState
    -0.56
    wpi
    -0.54
    GrantedAuthority
    -0.52
    hnia
    -0.52
     ModelExpression
    -0.52
    psack
    -0.50
    XmlAccessType
    -0.50
     Calvary
    -0.48
    POSITIVE LOGITS
    adaptiveStyles
    0.55
     malheure
    0.51
    ostante
    0.50
    PreferredItem
    0.48
    SourceChecksum
    0.48
    verwijspagina
    0.48
     lenker
    0.47
    licative
    0.47
     récomp
    0.47
     affichés
    0.46
    Activations Density 0.669%

    No Known Activations