© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10026
    Prev
    Next
    INDEX
    Explanations

    words relating to loss or something being missing

    oai_token-act-pair · gemini-2.0-flash

    missing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    EndInit
    -0.65
    EndGlobalSection
    -0.58
     Missing
    -0.56
    Missing
    -0.54
     disappeared
    -0.52
     desaparecido
    -0.51
     desapare
    -0.50
     Lost
    -0.47
     zag
    -0.47
     missing
    -0.46
    POSITIVE LOGITS
    thâu
    0.81
    theless
    0.72
    justed
    0.65
    titleMargin
    0.63
    yntaxException
    0.61
     internetowa
    0.60
     laughter
    0.60
    isable
    0.59
    出版年
    0.58
    itename
    0.55
    Activations Density 10.653%

    No Known Activations