© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14053
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs

    oai_token-act-pair · gemini-2.0-flash

    forms of the verb "sit"

    np_token-act-pair-logits · gpt-4o-mini

    body positions/movement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    pañol
    -0.56
     indietro
    -0.55
    DispatchToProps
    -0.53
    BaseType
    -0.50
     Diarsipkan
    -0.50
     convivencia
    -0.48
    base
    -0.47
    zinho
    -0.46
    )()
    -0.46
    WireFormat
    -0.46
    POSITIVE LOGITS
     sit
    0.86
     sat
    0.81
     sitting
    0.77
     Sit
    0.76
    Sit
    0.75
    IntoConstraints
    0.69
    Sitting
    0.68
     sits
    0.67
     standing
    0.66
    mbic
    0.64
    Activations Density 1.280%

    No Known Activations