© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 953
    Prev
    Next
    INDEX
    Explanations

    words, symbols, or parts of words that are related to negation or opposition, as well as a seemingly random assortment of other terms.

    oai_token-act-pair · gemini-2.0-flash

    non

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    t
    -1.41
    the
    -1.24
    d
    -1.14
    tattoo
    -1.08
    tone
    -1.05
    tory
    -1.05
    tl
    -1.05
    tren
    -1.00
    tur
    -0.99
    tan
    -0.98
    POSITIVE LOGITS
    й
    0.41
    ted
    0.40
    di
    0.40
    ات
    0.40
    able
    0.39
    cibly
    0.39
    <h5>
    0.38
    cerr
    0.37
    nnn
    0.37
    c
    0.36
    Activations Density 6.813%

    No Known Activations