© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9397
    Prev
    Next
    INDEX
    Explanations

    words related to people involved in legal or political events or arguments about them

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    putBoolean
    -0.59
    UVWXYZ
    -0.56
    пенно
    -0.56
    ടെ
    -0.51
     vectorielles
    -0.50
     orologio
    -0.50
     île
    -0.48
    adura
    -0.48
     giuri
    -0.48
    سجيلات
    -0.47
    POSITIVE LOGITS
    StoryboardSegue
    0.79
    interopRequire
    0.73
    TestingModule
    0.65
    igshid
    0.59
     comigo
    0.56
    templateUrl
    0.55
     okuyayım
    0.54
    Спољашње
    0.54
     незавершена
    0.53
    Diwedd
    0.52
    Activations Density 0.702%

    No Known Activations