© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8491
    Prev
    Next
    INDEX
    Explanations

    code snippets containing variations of "is/are/was [verb ending in -ed/-ing]."

    oai_token-act-pair · gemini-2.0-flash

    to be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ArrowToggle
    -0.81
    存于互联网档案馆
    -0.71
     للمعارف
    -0.67
    Koordinaten
    -0.67
    InjectAttribute
    -0.65
    Composable
    -0.65
     pleaſure
    -0.65
     themſelves
    -0.64
    ReusableCell
    -0.63
    RenderAtEndOf
    -0.63
    POSITIVE LOGITS
     hã
    0.56
     H
    0.56
    haël
    0.47
     stand
    0.47
    shant
    0.46
    пети
    0.45
    pushd
    0.44
     Hamilton
    0.43
     also
    0.43
     M
    0.43
    Activations Density 1.210%

    No Known Activations