© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15949
    Prev
    Next
    INDEX
    Explanations

    words about legal problems, hospitals, and prisons

    oai_token-act-pair · gemini-2.0-flash

    jail or prison

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    idemia
    -0.57
    ffindor
    -0.56
    uxxxx
    -0.53
    hahn
    -0.52
    Demografía
    -0.52
    BeginInit
    -0.51
    chromatic
    -0.50
    fully
    -0.50
     تانيه
    -0.49
    doma
    -0.48
    POSITIVE LOGITS
    rungsseite
    0.76
    AsUp
    0.59
    RegressionTest
    0.54
     estimés
    0.50
     jspb
    0.50
    Gambas
    0.50
    исленность
    0.49
    GIVEREF
    0.49
    Deel
    0.49
     densité
    0.48
    Activations Density 0.767%

    No Known Activations