© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8136
    Prev
    Next
    INDEX
    Explanations

    parts of text that are separators between reporting turns (likely in a conversation)

    oai_token-act-pair · gemini-2.0-flash

    Brazilian political scandals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    addCriterion
    -0.82
     resourceCulture
    -0.78
     <>",
    -0.70
     esternos
    -0.64
     ISNI
    -0.61
    SharedDtor
    -0.61
    mergeFrom
    -0.61
    netbeans
    -0.59
    awtextra
    -0.56
    LookAnd
    -0.53
    POSITIVE LOGITS
    PostExecute
    0.59
    fbox
    0.54
    einer
    0.50
    ividu
    0.50
    HomeAsUpEnabled
    0.49
    eft
    0.49
     algodão
    0.48
     orgasm
    0.47
    uride
    0.47
     getVersion
    0.46
    Activations Density 0.436%

    No Known Activations