© 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. 14147
    Prev
    Next
    INDEX
    Explanations

    time in months, after the words "follow-up"

    oai_token-act-pair · gemini-2.0-flash

    time units

    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
    ;'>
    -0.56
    ')):
    -0.55
    XmlAccessorType
    -0.54
    erstein
    -0.49
     &=&
    -0.48
    kunjung
    -0.48
     paddles
    -0.47
    balah
    -0.47
    achable
    -0.47
    ])[
    -0.47
    POSITIVE LOGITS
    Hentet
    0.63
    WebControls
    0.62
    expandindo
    0.61
    RegressionTest
    0.59
     defaultstate
    0.57
    aarrggbb
    0.56
    UnusedPrivate
    0.55
    WireFormat
    0.55
    OGND
    0.54
     שוליים
    0.54
    Activations Density 3.232%

    No Known Activations