© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5551
    Prev
    Next
    INDEX
    Explanations

    verbs in the past tense

    oai_token-act-pair · gemini-2.0-flash

    past tense verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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>
    -1.20
    multer
    -0.64
    The
    -0.60
    Demografie
    -0.58
     Meksiku
    -0.54
     The
    -0.50
    “
    -0.50
    <h2>
    -0.48
    <h3>
    -0.48
    ”
    -0.47
    POSITIVE LOGITS
    StructEnd
    0.64
     Himo
    0.62
     Emin
    0.60
    ForRow
    0.58
    FORMANCE
    0.58
     acetate
    0.57
    setVerticalGroup
    0.56
    ᅠ
    0.55
    انی
    0.54
     Obed
    0.54
    Activations Density 3.752%

    No Known Activations