© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7110
    Prev
    Next
    INDEX
    Explanations

    LaTeX code

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash

    say "single characters"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     L
    -1.59
     R
    -1.55
     S
    -1.54
     M
    -1.53
     P
    -1.48
     T
    -1.48
     D
    -1.47
     G
    -1.47
     C
    -1.45
     F
    -1.45
    POSITIVE LOGITS
    횟
    0.53
    Geplaatst
    0.50
     initComponents
    0.50
     MERCHANTABILITY
    0.50
     picado
    0.49
     rayures
    0.47
    ếc
    0.47
     rallado
    0.46
     CÁ
    0.46
     vectorielles
    0.46
    Activations Density 11.160%

    No Known Activations