© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12144
    Prev
    Next
    INDEX
    Explanations

    angle brackets, numbers, and the words "version", "artifactId", "groupId" and "key"

    oai_token-act-pair · gemini-2.0-flash

    "<"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    RegressionTest
    -0.66
    ftagPool
    -0.59
    RenderAtEndOf
    -0.52
     >>=
    -0.49
    gatsby
    -0.48
    kegaard
    -0.45
    Identyfik
    -0.45
    XmlIgnore
    -0.44
    AsUp
    -0.44
    URUS
    -0.44
    POSITIVE LOGITS
    AddTagHelper
    0.81
    IBOutlet
    0.59
    WriteTagHelper
    0.58
    rícula
    0.57
    ValueStyle
    0.57
    DataAnnotations
    0.56
    httphttps
    0.56
     HasFactory
    0.55
    uxxxx
    0.54
    цездатний
    0.54
    Activations Density 0.235%

    No Known Activations