© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9597
    Prev
    Next
    INDEX
    Explanations

    ordinal enumerators like "First", "Second", "Third"

    oai_token-act-pair · gemini-2.0-flash

    first second

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Second
    -1.73
     First
    -1.63
     Third
    -1.58
     Fourth
    -1.43
    Fourth
    -1.27
    Second
    -1.26
    Third
    -1.22
     Fifth
    -1.22
    Fifth
    -1.18
    First
    -1.10
    POSITIVE LOGITS
     first
    1.48
     second
    1.02
     last
    0.97
    first
    0.95
     first
    0.85
     third
    0.81
     earliest
    0.81
     primeiro
    0.80
     next
    0.79
     primeira
    0.78
    Activations Density 2.681%

    No Known Activations