© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12230
    Prev
    Next
    INDEX
    Explanations

    words and phrases that relate to research, evidence, academics, or legal issues

    oai_token-act-pair · gemini-2.0-flash

    indication or uncertainty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ंदीखरीदारी
    -0.79
     tartalomajánló
    -0.67
     cherchés
    -0.66
     مرئيه
    -0.62
     تانيه
    -0.61
     HttpNotFound
    -0.60
    Rhestr
    -0.60
    #+#
    -0.60
     betweenstory
    -0.60
    <bos>
    -0.59
    POSITIVE LOGITS
    tschaft
    0.49
     هيا
    0.49
    ktioner
    0.48
    setPreferredSize
    0.48
    argest
    0.47
     juger
    0.47
     carteira
    0.47
    sonaro
    0.46
    boer
    0.46
    iedler
    0.46
    Activations Density 48.422%

    No Known Activations