© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4000
    Prev
    Next
    INDEX
    Explanations

    references to time elapsing or something ceasing

    oai_token-act-pair · gemini-2.0-flash

    Foreign/code words

    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
     disappear
    -1.36
     disappearing
    -1.30
     disappeared
    -1.30
     disappearance
    -1.21
     disappears
    -1.20
     retiring
    -1.19
     vanished
    -1.16
     vanish
    -1.14
     withdraw
    -1.11
     removed
    -1.08
    POSITIVE LOGITS
    Hentet
    0.75
     SqlDbType
    0.71
    utilisons
    0.68
    hyrchwyd
    0.66
     estimés
    0.65
     BoxDecoration
    0.63
    ftagPool
    0.61
     للاسماء
    0.60
    [++
    0.60
    requestCode
    0.58
    Activations Density 0.530%

    No Known Activations