© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14633
    Prev
    Next
    INDEX
    Explanations

    intensifiers, specifically the word "very", sometimes followed by an adjective or the word "be"

    oai_token-act-pair · gemini-2.0-flash

    very

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     very
    -1.91
    Very
    -1.74
    very
    -1.64
     Very
    -1.60
     VERY
    -1.26
     muy
    -1.21
    VERY
    -1.17
     très
    -1.15
     muito
    -1.02
     molto
    -0.97
    POSITIVE LOGITS
    出版年
    0.84
     ***!
    0.82
     onAnimation
    0.79
    IonicModule
    0.79
     EconPapers
    0.77
    DOCTYPE
    0.76
    tagHelperRunner
    0.75
    enumii
    0.75
    SourceChecksum
    0.75
    mybatisplus
    0.75
    Activations Density 2.283%

    No Known Activations