© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12871
    Prev
    Next
    INDEX
    Explanations

    helping verbs linked to other words

    oai_token-act-pair · gemini-2.0-flash

    turn

    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
    ējās
    -0.52
    Personensuche
    -0.50
    LayoutPanel
    -0.49
    fortable
    -0.49
    données
    -0.49
     AssemblyProduct
    -0.48
    schedule
    -0.47
    jasmine
    -0.47
     gehad
    -0.47
    OUS
    -0.46
    POSITIVE LOGITS
     turn
    1.03
    turn
    0.91
     ста
    0.87
    Turn
    0.85
     turns
    0.84
     Turn
    0.81
     TURN
    0.81
     turned
    0.79
     turning
    0.75
    TURN
    0.73
    Activations Density 1.036%

    No Known Activations