© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16045
    Prev
    Next
    INDEX
    Explanations

    words indicating high emotional tension and conflict

    oai_token-act-pair · gemini-2.0-flash

    great

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ⓧ
    -0.64
    ///</
    -0.56
    Datuak
    -0.54
     disambiguazione
    -0.52
     AssemblyTitle
    -0.52
    InputBorder
    -0.50
    XMLSchema
    -0.50
    MessageTagHelper
    -0.49
     <>",
    -0.47
    #+#
    -0.47
    POSITIVE LOGITS
     great
    3.14
    great
    2.83
    Great
    2.53
     Great
    2.33
     GREAT
    2.23
    GREAT
    2.23
     greate
    1.48
     greats
    1.27
     greatest
    1.27
     terrific
    1.19
    Activations Density 5.094%

    No Known Activations