© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12215
    Prev
    Next
    INDEX
    Explanations

    the word "is"

    oai_token-act-pair · gemini-2.0-flash

    is

    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
     can
    -0.83
    ,
    -0.82
     are
    -0.77
     all
    -0.75
     so
    -0.75
     the
    -0.71
     
    -0.69
     a
    -0.65
     go
    -0.65
     in
    -0.64
    POSITIVE LOGITS
    InjectAttribute
    1.20
    GraphicsUnit
    1.01
     Efq
    1.00
     itſelf
    0.96
    <bos>
    0.96
     للاسماء
    0.95
    تقاوى
    0.93
     myſelf
    0.93
     виправивши
    0.93
     ſche
    0.90
    Activations Density 0.672%

    No Known Activations