© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7236
    Prev
    Next
    INDEX
    Explanations

    language comparing wind turbines to other things, frequently using the word "than"

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     loud
    -0.72
     Besøkt
    -0.63
     louder
    -0.63
     NOISE
    -0.63
     Noise
    -0.61
     noise
    -0.60
     volume
    -0.60
     deafening
    -0.59
     noisy
    -0.59
     shout
    -0.58
    POSITIVE LOGITS
    +#+#
    0.84
    twimg
    0.74
     Exacts
    0.73
    RTEX
    0.71
     tartalomajánló
    0.70
     betweenstory
    0.68
     متعلقه
    0.68
     @"/
    0.68
    脚注の使い方
    0.66
    deauna
    0.62
    Activations Density 0.858%

    No Known Activations