© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4691
    Prev
    Next
    INDEX
    Explanations

    references to the words "first", "last", "reaction", "right", or "dark"

    oai_token-act-pair · gemini-2.0-flash

    first

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Efq
    -1.53
     Jefus
    -1.33
     '\\;'
    -1.31
     myſelf
    -1.26
     himſelf
    -1.26
     themſelves
    -1.26
    IntoConstraints
    -1.24
     Houſe
    -1.23
     itſelf
    -1.23
    LookAnd
    -1.23
    POSITIVE LOGITS
      
    0.53
    T
    0.52
    ↵
    0.49
     T
    0.47
    ti
    0.42
        
    0.41
    [
    0.40
    /
    0.40
    <eos>
    0.40
    +
    0.40
    Activations Density 4.833%

    No Known Activations