© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5926
    Prev
    Next
    INDEX
    Explanations

    angle brackets and words related to color or animation, possibly in the context of web design

    oai_token-act-pair · gemini-2.0-flash

    <

    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
     autorytatywna
    -1.14
    ']?>
    -0.95
     EconPapers
    -0.87
     nahilalakip
    -0.85
    ThroughAttribute
    -0.85
     lenker
    -0.82
     صوتيه
    -0.81
     Normdatei
    -0.81
     jspb
    -0.81
    formik
    -0.80
    POSITIVE LOGITS
     productivo
    0.52
    playlists
    0.50
    cahontas
    0.48
     maș
    0.47
     Junge
    0.46
     calon
    0.45
    äsentation
    0.43
     tanker
    0.43
    —(
    0.42
     AppComponent
    0.41
    Activations Density 0.170%

    No Known Activations