© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7283
    Prev
    Next
    INDEX
    Explanations

    words that signify something changing or appearing

    oai_token-act-pair · gemini-2.0-flash

    emergence in formal writing

    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
    GEBURTSDATUM
    -0.99
    findpost
    -0.82
     defaultstate
    -0.77
     &___
    -0.72
     /\.(
    -0.72
     المعيارى
    -0.69
    DebuggerNonUser
    -0.67
     contextLoads
    -0.65
    Unmarshaller
    -0.65
    PreferredItem
    -0.63
    POSITIVE LOGITS
    sbericht
    0.49
    InstanceState
    0.49
     exigencias
    0.49
     from
    0.46
     venner
    0.46
     mulut
    0.43
    Performance
    0.43
     Performance
    0.40
    addContainerGap
    0.40
    performance
    0.40
    Activations Density 1.611%

    No Known Activations