© 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. 14989
    Prev
    Next
    INDEX
    Explanations

    words that commonly follow prepositions.

    oai_token-act-pair · gemini-2.0-flash

    words for "rather"

    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
    Very
    -0.79
     Very
    -0.75
    VERY
    -0.70
     quite
    -0.69
    very
    -0.69
     very
    -0.69
    Très
    -0.63
    quite
    -0.63
     muy
    -0.57
     Quite
    -0.56
    POSITIVE LOGITS
     rather
    3.44
    rather
    3.13
     Rather
    2.95
    Rather
    2.94
     plutôt
    2.38
     piuttosto
    2.25
    而不是
    1.70
    而非
    1.65
     vielmehr
    1.34
     anstatt
    1.34
    Activations Density 16.465%

    No Known Activations