© 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. 14430
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to being hired or accusations, particularly about money

    oai_token-act-pair · gemini-2.0-flash

    Actions and states of people

    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
     onData
    -0.54
    zeiger
    -0.47
    الحياه
    -0.47
    mung
    -0.46
    採
    -0.44
     geest
    -0.42
    unen
    -0.42
    em
    -0.41
     tilgjenge
    -0.41
    ören
    -0.41
    POSITIVE LOGITS
    tvguidetime
    0.91
    GraphicsUnit
    0.88
    AccessorTable
    0.80
    HostException
    0.76
     photolibrary
    0.75
     समीक्षक
    0.74
    المناصب
    0.73
     Efq
    0.70
     ModelExpression
    0.68
    ftagPool
    0.67
    Activations Density 2.509%

    No Known Activations