© 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. 3375
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions happening while doing something

    oai_token-act-pair · 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
     wireType
    -0.47
    SizeF
    -0.45
     race
    -0.44
    trade
    -0.41
    dance
    -0.41
     racer
    -0.39
     itemprop
    -0.38
     racers
    -0.38
    faker
    -0.38
    rest
    -0.38
    POSITIVE LOGITS
    Vidite
    0.68
     kasarigan
    0.68
    arXiv
    0.66
     snippetHide
    0.60
    monių
    0.59
     collapsed
    0.57
    thora
    0.56
    êmica
    0.55
     Unies
    0.55
    èze
    0.55
    Activations Density 1.959%

    No Known Activations