© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12772
    Prev
    Next
    INDEX
    Explanations

    phrases meaning `seems like something is` or `to be`.

    oai_token-act-pair · gemini-2.0-flash

    seem

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    -0.95
    abestanden
    -0.90
     étoient
    -0.86
    parsedMessage
    -0.85
     nahilalakip
    -0.84
    AddTagHelper
    -0.83
    SharedCtor
    -0.82
     resourceCulture
    -0.82
    Datuak
    -0.80
     Мексичка
    -0.78
    POSITIVE LOGITS
     to
    0.95
     most
    0.54
    setModal
    0.53
     a
    0.49
     su
    0.49
     critical
    0.49
     fond
    0.48
     way
    0.48
    dz
    0.47
     el
    0.46
    Activations Density 7.148%

    No Known Activations