© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12914
    Prev
    Next
    INDEX
    Explanations

    words, phrases, and sentences about events, particularly those involving receiving autographs or attending concerts

    oai_token-act-pair · gemini-2.0-flash

    references to auto-related items

    np_token-act-pair-logits · gpt-4o-mini

    autographs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    তথ্যসূত্র
    -0.54
     otomatig
    -0.51
    énario
    -0.48
    ValueGenerated
    -0.47
    ടെ
    -0.47
    響
    -0.47
    WithIOException
    -0.47
     continúas
    -0.46
     noten
    -0.45
     interpreting
    -0.44
    POSITIVE LOGITS
     auto
    1.31
     Auto
    1.10
    auto
    1.09
    Auto
    1.02
     AUTO
    0.96
     autos
    0.81
    AUTO
    0.79
     Autos
    0.74
    ]--;
    0.69
     signed
    0.68
    Activations Density 1.225%

    No Known Activations