© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11734
    Prev
    Next
    INDEX
    Explanations

    the phrase "line of" or the word "line".

    oai_token-act-pair · gemini-2.0-flash

    line

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     line
    -2.98
     lines
    -2.80
     Line
    -2.72
    line
    -2.64
    Line
    -2.63
     Lines
    -2.61
    lines
    -2.56
     LINE
    -2.41
    Lines
    -2.41
    LINE
    -2.38
    POSITIVE LOGITS
    IntoConstraints
    0.85
     ujednoznacz
    0.64
    thâu
    0.63
    曖昧さ回避
    0.61
    PMailer
    0.61
     nakalista
    0.56
     NSCoder
    0.54
    rungsseite
    0.54
    Attribution
    0.53
     Италијани
    0.53
    Activations Density 2.114%

    No Known Activations