© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8000
    Prev
    Next
    INDEX
    Explanations

    present tense verbs, and words related to making an impact

    oai_token-act-pair · gemini-2.0-flash

    photograph

    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
    Negative Logits
    RegressionTest
    -0.79
    verifyException
    -0.55
     }{@
    -0.52
    enuto
    -0.50
    ISupport
    -0.50
    enumii
    -0.47
    ngdoc
    -0.47
     مرئيه
    -0.46
     Manchuria
    -0.46
     ứng
    -0.45
    POSITIVE LOGITS
    JspWriter
    0.60
    addCriterion
    0.56
    AnchorStyles
    0.52
    GEBURTSDATUM
    0.52
     boucles
    0.51
     Plotting
    0.50
    انيف
    0.50
    PickerController
    0.49
     ProtoMessage
    0.49
    ishable
    0.47
    Activations Density 1.092%

    No Known Activations