© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 638
    Prev
    Next
    INDEX
    Explanations

    words that describe art, architecture, events, or emotions, specifically with positive or negative connotations

    oai_token-act-pair · gemini-2.0-flash

    reviews and recommendations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     CreateTagHelper
    -0.53
    oredCriteria
    -0.51
    adpleegd
    -0.51
    RegressionTest
    -0.47
    tagext
    -0.47
     Geraadpleegd
    -0.46
    AddTagHelper
    -0.45
     ویکی‌پدی
    -0.45
     nosotros
    -0.45
    новниш
    -0.44
    POSITIVE LOGITS
    tershire
    0.68
     EClass
    0.67
    XmlRootElement
    0.64
    >>>>>>>
    0.63
    cedent
    0.63
     Référence
    0.61
    tradition
    0.60
    NUMX
    0.59
    shadowColor
    0.59
    ousand
    0.59
    Activations Density 2.470%

    No Known Activations