© 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
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 9481
    Prev
    Next
    INDEX
    Explanations

    the word "either" as well as words related to decisions and instructions

    oai_token-act-pair · gemini-2.0-flash

    either

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    both
    -0.43
    一旦
    -0.39
    Both
    -0.39
    Cubit
    -0.36
     invece
    -0.35
     both
    -0.35
    Gecko
    -0.35
    فاوت
    -0.34
     sorprender
    -0.33
    とは思
    -0.33
    POSITIVE LOGITS
    parsedMessage
    0.95
    ValueStyle
    0.77
     שוליים
    0.70
     arşivlendi
    0.68
     Normdatei
    0.67
    IntoConstraints
    0.66
    LabelTagHelper
    0.66
    UnknownFieldSet
    0.65
    ViewFeatures
    0.62
    astify
    0.62
    Activations Density 6.779%

    No Known Activations