© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11325
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to pregnancy and birth control

    oai_token-act-pair · gemini-2.0-flash

    reproductive rights/birth control

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     reproductive
    -0.63
    EndGlobalSection
    -0.63
    principalTable
    -0.59
    TestingModule
    -0.58
     reproduction
    -0.57
     mapStateToProps
    -0.57
     <=",
    -0.56
     estekak
    -0.56
     ModelExpression
    -0.56
     gend
    -0.56
    POSITIVE LOGITS
    InteropServices
    0.53
     tourné
    0.47
     AI
    0.47
    httphttps
    0.46
     henvisninger
    0.45
    alin
    0.44
     layui
    0.44
     artificial
    0.43
    esa
    0.43
    orea
    0.43
    Activations Density 1.622%

    No Known Activations