© 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. 11926
    Prev
    Next
    INDEX
    Explanations

    text within parenthesis or around dashes or asterisks, possibly asides or parenthetical statements

    oai_token-act-pair · gemini-2.0-flash

    open parenthesis

    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
     getItemId
    -0.76
    ConstraintMaker
    -0.74
     considérons
    -0.70
     InputDecoration
    -0.70
     fortunately
    -0.68
     unfortunately
    -0.66
    WebVitals
    -0.66
     contextLoads
    -0.66
     <<<<<<<<<<<<<<
    -0.65
     jadx
    -0.65
    POSITIVE LOGITS
     pauvreté
    0.46
    CURSO
    0.45
    harma
    0.43
    orated
    0.42
    harry
    0.42
     extérieures
    0.42
    Chúng
    0.42
    können
    0.42
    huff
    0.42
    welche
    0.41
    Activations Density 8.451%

    No Known Activations