© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9295
    Prev
    Next
    INDEX
    Explanations

    words and numbers included in parentheses, brackets, references, and lists especially when associated with medical or scientific topics.

    oai_token-act-pair · gemini-2.0-flash

    examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     benne
    -0.60
    AddAttribute
    -0.60
     fédé
    -0.60
     généraux
    -0.58
     createSprite
    -0.58
     Efq
    -0.58
    posób
    -0.57
     pleaſure
    -0.57
    iconque
    -0.57
    ACITY
    -0.57
    POSITIVE LOGITS
     learned
    0.50
    setSubject
    0.48
     JsonConvert
    0.47
     LoginForm
    0.47
    «
    0.47
     setPassword
    0.46
    kawaii
    0.46
     useParams
    0.46
    gitlab
    0.45
    「
    0.45
    Activations Density 2.795%

    No Known Activations