© 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. 1124
    Prev
    Next
    INDEX
    Explanations

    uses of the words 'a', 'the', and 'my', and is also activated by phrases like "we have" or "there is"

    oai_token-act-pair · 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
    __":
    -0.71
    __':
    -0.61
    ()}}
    -0.55
    migrationBuilder
    -0.51
     defStyle
    -0.50
    withIdentifier
    -0.48
    )})
    -0.46
    setViewportView
    -0.45
     uLocal
    -0.44
    äsent
    -0.44
    POSITIVE LOGITS
    twimg
    0.75
    MessageState
    0.65
     surprises
    0.57
    ISupport
    0.55
    hidupan
    0.54
    kter
    0.53
     ftate
    0.53
     promozione
    0.52
    ಂತ
    0.52
     Dying
    0.52
    Activations Density 0.863%

    No Known Activations