© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12699
    Prev
    Next
    INDEX
    Explanations

    the word "plus" and related javascript variables like "clickPlus."

    oai_token-act-pair · gemini-2.0-flash

    Plus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     plus
    -2.83
    Plus
    -2.80
    plus
    -2.80
     Plus
    -2.64
     PLUS
    -2.28
    PLUS
    -2.25
     плюс
    -1.65
     minus
    -1.28
    minus
    -1.25
    Minus
    -1.09
    POSITIVE LOGITS
     endforeach
    0.63
    IsPostBack
    0.62
    SPATH
    0.62
    mello
    0.56
    batore
    0.55
    formik
    0.54
    arResult
    0.52
    IActionResult
    0.52
     sauvages
    0.52
    ScopeManager
    0.50
    Activations Density 1.956%

    No Known Activations