© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8325
    Prev
    Next
    INDEX
    Explanations

    references to time periods or temporal context

    oai_token-act-pair · gemini-2.0-flash

    Time scales

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    richTextPanel
    -0.81
    CloseOperation
    -0.79
    ValueStyle
    -0.74
     StatelessWidget
    -0.70
    invokeLater
    -0.68
    ViewFeatures
    -0.66
    SequentialGroup
    -0.66
    MLLoader
    -0.65
     ActivatedRoute
    -0.65
    __*/
    -0.63
    POSITIVE LOGITS
     Efq
    0.49
     متعلقه
    0.48
     noDo
    0.48
     Anſ
    0.47
     springfox
    0.46
     firſt
    0.46
     COT
    0.46
     Oedipus
    0.45
     poffe
    0.44
     LTS
    0.44
    Activations Density 3.934%

    No Known Activations