© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11547
    Prev
    Next
    INDEX
    Explanations

    ordinal indicators like *First*, *Second*, *Finally*, *The* and connecting language like *Then* and *In addition*

    oai_token-act-pair · gemini-2.0-flash

    the word "second"

    np_token-act-pair-logits · gpt-4o-mini

    second

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    First
    -0.51
     First
    -0.50
    まず
    -0.47
     Firstly
    -0.46
     also
    -0.46
    Personendaten
    -0.45
     اطلع
    -0.44
     JpaRepository
    -0.44
     сначала
    -0.41
    unum
    -0.41
    POSITIVE LOGITS
     second
    2.94
    second
    2.66
    Second
    2.38
    SECOND
    2.25
     Second
    2.20
     SECOND
    2.19
     segundo
    2.05
     deuxième
    2.02
     seconde
    2.00
     segunda
    1.99
    Activations Density 5.796%

    No Known Activations