© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5591
    Prev
    Next
    INDEX
    Explanations

    text related to land and property development regulations

    oai_token-act-pair · gemini-2.0-flash

    technical documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    abetes
    -0.66
     MainAxisSize
    -0.59
    ViewFeatures
    -0.59
    TagMode
    -0.54
    談社
    -0.52
    forRoot
    -0.51
    FormTagHelper
    -0.51
    ValueGeneration
    -0.50
    帖最后由
    -0.49
    makeText
    -0.49
    POSITIVE LOGITS
    oredCriteria
    0.59
    awaiter
    0.59
    DebuggerStep
    0.50
    aktery
    0.49
    FieldBuilder
    0.48
     Qualification
    0.48
    zise
    0.47
    AntiForgeryToken
    0.47
    nio
    0.46
    oneofs
    0.46
    Activations Density 18.303%

    No Known Activations