© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13194
    Prev
    Next
    INDEX
    Explanations

    instances of "I don't know" and similar phrases.

    oai_token-act-pair · gemini-2.0-flash

    know

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    migrationBuilder
    -0.81
    Personendaten
    -0.77
    enumii
    -0.70
    HomeAsUpEnabled
    -0.68
    TestTools
    -0.68
     oprot
    -0.67
    aarrggbb
    -0.67
    BeginContext
    -0.64
     DST
    -0.64
    ScopeManager
    -0.63
    POSITIVE LOGITS
     any
    0.75
     anyone
    0.73
     that
    0.70
     about
    0.69
     anything
    0.64
     yet
    0.63
     anywhere
    0.63
    ANY
    0.62
     anytime
    0.61
     ANY
    0.60
    Activations Density 1.565%

    No Known Activations