© 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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 12739
    Prev
    Next
    INDEX
    Explanations

    the word "otherwise"

    oai_token-act-pair · gemini-2.0-flash

    otherwise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.23
    Dona
    -0.54
    '
    -0.51
    let
    -0.50
    '`
    -0.49
     adb
    -0.47
     assoluto
    -0.46
     alimentaires
    -0.46
    Tradu
    -0.45
     forme
    -0.44
    POSITIVE LOGITS
    ConstraintMaker
    0.79
    RepeatedField
    0.69
     distanciation
    0.69
    tagHelperRunner
    0.68
    braio
    0.68
     nonatomic
    0.67
    sourced
    0.67
    BeginContext
    0.67
    aneity
    0.66
    ariously
    0.66
    Activations Density 1.549%

    No Known Activations