© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15129
    Prev
    Next
    INDEX
    Explanations

    words indicating time

    oai_token-act-pair · gemini-2.0-flash

    conjunctions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     humaines
    -0.63
     whilst
    -0.62
     pouvoirs
    -0.58
     mocy
    -0.56
     Whilst
    -0.56
     kereszt
    -0.55
    ↵↵
    -0.55
     emberek
    -0.54
     verkoop
    -0.54
     legales
    -0.54
    POSITIVE LOGITS
    NUMX
    0.95
     MessageBoxIcon
    0.85
     snippetHide
    0.83
     doInBackground
    0.80
    SuppressLint
    0.75
    UserScript
    0.72
    Bronnen
    0.68
    存于互联网档案馆
    0.67
    uttavia
    0.64
    URIComponent
    0.63
    Activations Density 0.560%

    No Known Activations