© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13482
    Prev
    Next
    INDEX
    Explanations

    phrases, particularly prepositional phrases, related to accomplishing some goal and following a path to it

    oai_token-act-pair · gemini-2.0-flash

    words related to paths or routes

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

    road and path

    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
     unknownFields
    -0.81
     Meksiku
    -0.78
     resourceCulture
    -0.76
     betweenstory
    -0.72
     ostavi
    -0.70
     становника
    -0.69
    twimg
    -0.67
    apunov
    -0.67
    usercontent
    -0.66
     EconPapers
    -0.66
    POSITIVE LOGITS
     road
    2.59
     path
    2.17
    road
    2.13
     Road
    2.03
    Road
    2.02
     route
    1.95
     ROAD
    1.91
    path
    1.86
     roads
    1.80
    ROAD
    1.80
    Activations Density 2.343%

    No Known Activations