© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2875
    Prev
    Next
    INDEX
    Explanations

    words indicating an opinion or decision about something

    oai_token-act-pair · gemini-2.0-flash

    figure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     فريبيس
    -0.63
    ρέ
    -0.56
    forma
    -0.54
    RegressionTest
    -0.54
     ran
    -0.49
    udad
    -0.47
    pondi
    -0.46
    alamu
    -0.46
    遵
    -0.46
    ########.
    -0.45
    POSITIVE LOGITS
    ImageContext
    0.84
     ་་
    0.77
     Jefus
    0.77
     Efq
    0.77
     ſtate
    0.77
     Houſe
    0.75
     houſe
    0.72
     Chriftian
    0.72
     rodríguez
    0.71
     purpoſe
    0.71
    Activations Density 1.853%

    No Known Activations