© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10355
    Prev
    Next
    INDEX
    Explanations

    articles and prepositions and their surrounding words

    oai_token-act-pair · gemini-2.0-flash

    prefixes 'pre-'

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

    pre

    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
     Efq
    -1.02
     Theſe
    -0.88
     initComponents
    -0.84
     Jefus
    -0.84
     ſche
    -0.80
     myſelf
    -0.78
    InjectAttribute
    -0.77
     pleaſure
    -0.77
     Monfieur
    -0.76
     Chriftian
    -0.75
    POSITIVE LOGITS
     pre
    3.63
    pre
    2.94
    Pre
    2.89
     Pre
    2.83
     PRE
    2.34
     pré
    2.33
    PRE
    2.31
    预
    2.02
     prer
    1.77
     pred
    1.59
    Activations Density 4.572%

    No Known Activations