© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12473
    Prev
    Next
    INDEX
    Explanations

    words ending in "al" especially those related to medicine, science, and law

    oai_token-act-pair · gemini-2.0-flash

    ological

    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
    letal
    -0.70
    ULAR
    -0.70
    IONAL
    -0.69
    culous
    -0.67
    NOSTIC
    -0.66
    chymal
    -0.66
     musical
    -0.64
    astic
    -0.64
    icular
    -0.63
    ONIC
    -0.63
    POSITIVE LOGITS
    tagHelperRunner
    0.93
     itſelf
    0.75
     ejus
    0.74
    
    0.72
     quæ
    0.70
     raiſ
    0.67
    RegressionTest
    0.65
    +#+#
    0.63
    bcryptjs
    0.61
    MessageTagHelper
    0.60
    Activations Density 4.851%

    No Known Activations