© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6963
    Prev
    Next
    INDEX
    Explanations

    words that describe newness, originality, or surprise

    oai_token-act-pair · gemini-2.0-flash

    variants of "new"/"novel"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    Бахар
    -0.64
     ModelExpression
    -0.63
    хьтан
    -0.63
    RTLR
    -0.61
    SharedDtor
    -0.60
     SIMBAD
    -0.60
     ffilmiau
    -0.59
    AndEndTag
    -0.59
    MENAFN
    -0.57
    aryen
    -0.57
    POSITIVE LOGITS
     new
    2.06
    new
    1.89
     novel
    1.48
     nuevo
    1.47
     nuevos
    1.46
    新的
    1.41
     nuovo
    1.41
     nueva
    1.40
     nuevas
    1.40
     nuove
    1.38
    Activations Density 2.547%

    No Known Activations