© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10853
    Prev
    Next
    INDEX
    Explanations

    punctuation in some contexts, likely related to adjacent tokens

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    <bos>
    -0.57
    存于互联网档案馆
    -0.52
    ?}",
    -0.50
    WritableDatabase
    -0.50
    keta
    -0.49
    Abitanti
    -0.48
    הערות
    -0.47
    typeorm
    -0.47
    imetsu
    -0.47
     resourceCulture
    -0.47
    POSITIVE LOGITS
    ArrowToggle
    0.62
     fapt
    0.55
    zeczytaj
    0.52
    पया
    0.52
    ıyoruz
    0.50
     blest
    0.50
    mıştır
    0.50
     calendriers
    0.49
     sanitaires
    0.49
     csomag
    0.49
    Activations Density 2.157%

    No Known Activations