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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1213
    Prev
    Next
    INDEX
    Explanations

    words about public communication and sales

    oai_token-act-pair · 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
     reader
    -1.57
    reader
    -1.45
     Reader
    -1.43
     viewer
    -1.38
     visitor
    -1.32
    Reader
    -1.29
     buyer
    -1.27
     Readers
    -1.27
     Buyer
    -1.26
     readers
    -1.25
    POSITIVE LOGITS
    DockStyle
    0.76
    FormTagHelper
    0.68
    Enllaces
    0.65
    oredCriteria
    0.62
    IsContent
    0.60
    featureID
    0.59
    InstrumentedTest
    0.59
    ComponentModel
    0.57
    الإنجليزية
    0.56
    EndInit
    0.55
    Activations Density 2.569%

    No Known Activations