© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 677
    Prev
    Next
    INDEX
    Explanations

    phrases expressing wanting or wishing to do something

    oai_token-act-pair · gemini-2.0-flash

    seeing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     للاسماء
    -0.51
    contentLoaded
    -0.50
    InstrumentedTest
    -0.48
    matchCondition
    -0.48
     understanding
    -0.44
     o
    -0.42
    understanding
    -0.42
     виправивши
    -0.42
     @"/
    -0.40
     O
    -0.39
    POSITIVE LOGITS
     seeing
    1.26
     see
    1.16
     sees
    1.07
     seen
    1.06
    See
    1.05
    seeing
    1.05
     saw
    1.05
     See
    1.02
     SEE
    0.99
     voir
    0.95
    Activations Density 0.728%

    No Known Activations