© 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. 2069
    Prev
    Next
    INDEX
    Explanations

    instances of discovery or awareness

    oai_token-act-pair · gemini-2.0-flash

    noticing something

    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
     rege
    -0.50
    もちゃ
    -0.48
     Lordships
    -0.47
     Antiquity
    -0.44
     powietrza
    -0.42
     eternally
    -0.42
     slowest
    -0.42
     Piso
    -0.40
     näh
    -0.40
     NIP
    -0.39
    POSITIVE LOGITS
     some
    0.64
    <bos>
    0.60
     that
    0.59
     lots
    0.57
     this
    0.56
    AnimationsModule
    0.56
     them
    0.56
     what
    0.55
     a
    0.54
    FACES
    0.54
    Activations Density 5.497%

    No Known Activations