© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11554
    Prev
    Next
    INDEX
    Explanations

    words related to taxes, medical conditions, political unrest, technical issues, and war

    oai_token-act-pair · gemini-2.0-flash

    tax-related terms and concepts

    np_token-act-pair-logits · gpt-4o-mini
    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
     autorytatywna
    -0.76
    ValueStyle
    -0.74
    migrationBuilder
    -0.74
    帖最后由
    -0.73
    Autoritní
    -0.63
     calendriers
    -0.63
    TestingModule
    -0.59
      (
    -0.58
    principalTable
    -0.57
    aarrggbb
    -0.56
    POSITIVE LOGITS
    niająca
    0.57
     IconData
    0.54
     durs
    0.53
    ElementException
    0.52
    SurfaceView
    0.52
    AndFlush
    0.52
    PyExc
    0.52
     to
    0.52
    μφωνα
    0.52
    stehen
    0.51
    Activations Density 5.628%

    No Known Activations