© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3060
    Prev
    Next
    INDEX
    Explanations

    the numbers thirty and forty

    oai_token-act-pair · gemini-2.0-flash

    thirty or forty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     calendriers
    -0.88
     Roskov
    -0.85
    ThroughAttribute
    -0.82
    يكب
    -0.81
    Vidite
    -0.80
    styleType
    -0.80
     Meksiku
    -0.79
    PYX
    -0.78
    astéroïdes
    -0.77
     Paglinawan
    -0.77
    POSITIVE LOGITS
     a
    0.59
    ↵
    0.58
    </b>
    0.55
     
    0.54
    ↵↵
    0.51
    ביוגרפיה
    0.51
     espirituales
    0.50
     T
    0.50
    </i>
    0.50
    <h2>
    0.49
    Activations Density 0.344%

    No Known Activations