© 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. 12475
    Prev
    Next
    INDEX
    Explanations

    hyphens and other punctuation in a document.

    oai_token-act-pair · gemini-2.0-flash

    -

    np_max-act-logits · gemini-2.0-flash
    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
    -0.87
    la
    -0.84
    lf
    -0.83
    li
    -0.80
    le
    -0.77
    lapp
    -0.74
    ly
    -0.72
    lc
    -0.72
    lin
    -0.71
    lv
    -0.69
    POSITIVE LOGITS
    mos
    0.54
    mi
    0.52
    män
    0.51
    m
    0.51
    man
    0.51
    mo
    0.51
    TagMode
    0.49
    mons
    0.47
    mma
    0.47
    mes
    0.47
    Activations Density 15.008%

    No Known Activations