© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6670
    Prev
    Next
    INDEX
    Explanations

    technical vocabulary related to the natural sciences

    oai_token-act-pair · gemini-2.0-flash

    forests and trees

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     préférence
    -0.50
    maining
    -0.50
    енко
    -0.46
     extérieurs
    -0.46
    ourse
    -0.45
     payé
    -0.45
    ETYPE
    -0.44
    RetentionPolicy
    -0.44
     hombros
    -0.44
    tvguidetime
    -0.43
    POSITIVE LOGITS
    <bos>
    0.96
     Shakspeare
    0.66
     placebo
    0.65
     Muses
    0.64
     Greenland
    0.61
     diarr
    0.60
    TacToe
    0.60
     विश्वसनीयता
    0.60
     parseFrom
    0.59
     edifice
    0.58
    Activations Density 4.181%

    No Known Activations