© 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. 9742
    Prev
    Next
    INDEX
    Explanations

    code snippets in Python that perform data manipulation using pandas and numpy

    oai_token-act-pair · gemini-2.0-flash

    python code

    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
    didSet
    -0.76
    >{@
    -0.74
    tvguidetime
    -0.73
    bagno
    -0.69
     tasche
    -0.68
     récents
    -0.68
    cemment
    -0.67
    Voci
    -0.66
    Biografía
    -0.66
     personnalisée
    -0.66
    POSITIVE LOGITS
    <bos>
    0.81
    IContainer
    0.57
    jsdelivr
    0.49
     nahilalakip
    0.48
    IntoConstraints
    0.44
    การณ์
    0.43
    TabIndex
    0.43
    awtextra
    0.43
     im
    0.41
     eventdata
    0.41
    Activations Density 2.105%

    No Known Activations