© 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. 15628
    Prev
    Next
    INDEX
    Explanations

    words ending in "-ise" or "-ize", and words with similar suffixes.

    oai_token-act-pair · gemini-2.0-flash

    scientific writing

    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
     autorytatywna
    -0.54
     satunya
    -0.40
    parametrize
    -0.40
    aperto
    -0.39
     وما
    -0.38
     до
    -0.37
    ::_('
    -0.37
    vera
    -0.36
    cO
    -0.36
     fa
    -0.35
    POSITIVE LOGITS
     betweenstory
    0.88
     StringTokenizer
    0.69
    ModelBuilder
    0.68
     protoimpl
    0.68
     resourceCulture
    0.66
    WithIOException
    0.65
    TintMode
    0.64
     kasarigan
    0.63
     صوتيه
    0.63
     OFDb
    0.60
    Activations Density 2.302%

    No Known Activations