© 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. 9759
    Prev
    Next
    INDEX
    Explanations

    terms related to housing and building construction

    oai_token-act-pair · gemini-2.0-flash

    buildings and rooms

    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
     ſtate
    -0.77
     greateſt
    -0.76
     houſe
    -0.74
    StoreMessageInfo
    -0.73
     myſelf
    -0.72
     auroit
    -0.70
     beſt
    -0.69
     himſelf
    -0.68
     cauſe
    -0.68
    WithIOException
    -0.68
    POSITIVE LOGITS
    ↵↵
    0.85
    '
    0.72
    <bos>
    0.62
    ↵
    0.60
    ’
    0.52
    {
    0.49
    <eos>
    0.48
    deaux
    0.46
    ✨:
    0.45
    oyi
    0.45
    Activations Density 1.072%

    No Known Activations