© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12331
    Prev
    Next
    INDEX
    Explanations

    code snippets related to React components and UI elements

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    TypedDataSet
    -0.75
     noDo
    -0.74
    stdc
    -0.68
    featureID
    -0.66
     []:
    -0.60
    contentLoaded
    -0.60
    jooq
    -0.57
    :+:
    -0.56
    Personensuche
    -0.55
    ']):
    -0.55
    POSITIVE LOGITS
     lány
    0.65
     dieux
    0.63
     vierge
    0.60
     fotografico
    0.60
     vermelhas
    0.59
     insegna
    0.59
     locaux
    0.58
     tryck
    0.58
     varandra
    0.57
     meille
    0.57
    Activations Density 2.617%

    No Known Activations