© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4481
    Prev
    Next
    INDEX
    Explanations

    expressions of doubt or speculation starting with a question word like "whether" or "if"

    oai_token-act-pair · gemini-2.0-flash

    if/whether

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    whether
    -0.79
     WHETHER
    -0.75
     whether
    -0.75
     Whether
    -0.69
    Whether
    -0.66
     ikiwa
    -0.52
    échelle
    -0.51
    audiovisuel
    -0.50
    是否是
    -0.49
    if
    -0.49
    POSITIVE LOGITS
     propOrder
    0.80
    الحياه
    0.77
    WithIOException
    0.77
    RenderAtEndOf
    0.70
     ویکی‌پدیا
    0.69
    LookAnd
    0.65
     ComVisible
    0.63
     &___
    0.63
    SharedCtor
    0.61
     AttributeSet
    0.60
    Activations Density 1.117%

    No Known Activations