© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10678
    Prev
    Next
    INDEX
    Explanations

    a linking word or phrase, frequently "but," around which the text presents a contrasting idea.

    oai_token-act-pair · gemini-2.0-flash

    but

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Савезне
    -0.63
    Tembelea
    -0.55
    alternate
    -0.49
     sebaliknya
    -0.48
    どうなる
    -0.47
     infatti
    -0.46
    מת
    -0.46
     Apalagi
    -0.44
    ilarang
    -0.44
    Nor
    -0.43
    POSITIVE LOGITS
     rather
    2.81
    rather
    2.42
     Rather
    2.39
    Rather
    2.34
     piuttosto
    1.91
     plutôt
    1.76
    而不是
    1.26
    而非
    1.25
    setVerticalGroup
    0.96
     eher
    0.94
    Activations Density 4.866%

    No Known Activations