© 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. 14382
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to formal studies

    oai_token-act-pair · gemini-2.0-flash

    scientific/technical studies

    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
     subject
    -3.17
     Subject
    -3.08
    Subject
    -3.02
    subject
    -3.00
     subjects
    -2.77
     SUBJECT
    -2.67
     Subjects
    -2.59
    SUBJECT
    -2.55
    subjects
    -2.41
    Subjects
    -2.36
    POSITIVE LOGITS
    RegressionTest
    0.65
    mybatisplus
    0.55
     LAYER
    0.51
    ReusableCell
    0.50
     layer
    0.49
     Quig
    0.48
    LayoutPanel
    0.48
    TypedDataSet
    0.48
    Resolver
    0.48
    führt
    0.47
    Activations Density 5.517%

    No Known Activations