© 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. 3906
    Prev
    Next
    INDEX
    Explanations

    words associated with reflection on past events.

    oai_token-act-pair · gemini-2.0-flash

    Continuing thoughts

    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
    []>
    -0.49
    NOPQRST
    -0.47
    Gön
    -0.45
     Kit
    -0.44
     fmt
    -0.42
    Pri
    -0.42
     Brad
    -0.41
    #+#
    -0.41
    hdashline
    -0.41
    بدو
    -0.40
    POSITIVE LOGITS
    NameInMap
    0.70
    parsedMessage
    0.67
     damals
    0.64
     immediate
    0.64
    Smarty
    0.62
    当時は
    0.62
    BufferException
    0.59
     currently
    0.59
    Cursors
    0.59
    databinding
    0.58
    Activations Density 1.668%

    No Known Activations