© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3246
    Prev
    Next
    INDEX
    Explanations

    code or other identifiers

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
     صوتيه
    -0.68
    tagHelperRunner
    -0.59
     CreateTagHelper
    -0.57
    XmlAccessType
    -0.52
    RegistryLite
    -0.52
    TypedDataSet
    -0.51
    InteropServices
    -0.50
    nonatomic
    -0.49
     StatelessWidget
    -0.47
     big
    -0.46
    POSITIVE LOGITS
    ItemBackground
    0.66
    usercontent
    0.61
    djangoproject
    0.56
     répondu
    0.52
     transparentes
    0.52
    PostInfinity
    0.52
    BagConstraints
    0.51
    batore
    0.51
     geleverd
    0.50
    gebnissen
    0.50
    Activations Density 1.858%

    No Known Activations