© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13956
    Prev
    Next
    INDEX
    Explanations

    words in legal or medical documents relating to a person's stay in a medical or correctional institute

    oai_token-act-pair · gemini-2.0-flash

    Prisons/rooms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Efq
    -0.79
    ագրություններ
    -0.79
    RegressionTest
    -0.73
    ⓧ
    -0.71
    تقاوى
    -0.71
    ItemBackground
    -0.67
    SequentialGroup
    -0.64
     Paglinawan
    -0.63
     ModelExpression
    -0.63
    GraphicsUnit
    -0.63
    POSITIVE LOGITS
     king
    0.52
    king
    0.48
    tuber
    0.47
     master
    0.47
    Connecting
    0.47
     King
    0.46
     iVar
    0.46
     Engels
    0.45
    дям
    0.45
    master
    0.44
    Activations Density 1.500%

    No Known Activations