© 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. 7264
    Prev
    Next
    INDEX
    Explanations

    words relating to fixing or placement

    oai_token-act-pair · gemini-2.0-flash

    placed

    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
     placed
    -2.23
     Placed
    -1.95
    placed
    -1.95
     placing
    -1.91
     placement
    -1.83
    Placed
    -1.82
     Placing
    -1.73
     placements
    -1.66
     Placement
    -1.66
    placing
    -1.62
    POSITIVE LOGITS
    PropertyChanging
    0.65
    bride
    0.56
    ätzlich
    0.56
    FUEL
    0.52
    dengar
    0.52
    ($__
    0.52
     Gonçalves
    0.51
    MigrationBuilder
    0.50
    acuzzi
    0.50
    atitis
    0.49
    Activations Density 3.135%

    No Known Activations