© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11866
    Prev
    Next
    INDEX
    Explanations

    words that describe effort, progress, or forward momentum

    oai_token-act-pair · gemini-2.0-flash

    Movement and force

    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
     fumée
    -0.73
     nôtre
    -0.72
     affari
    -0.69
     esercit
    -0.66
     hiér
    -0.65
     propOrder
    -0.64
     goutte
    -0.64
     circonst
    -0.64
     vôtre
    -0.63
     poussière
    -0.63
    POSITIVE LOGITS
     flow
    0.96
     grip
    0.87
     cycle
    0.69
    :+:
    0.69
     pace
    0.68
    flow
    0.66
     pull
    0.65
     momentum
    0.64
     bond
    0.61
     grasp
    0.60
    Activations Density 3.002%

    No Known Activations