© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11262
    Prev
    Next
    INDEX
    Explanations

    the word "locally"

    oai_token-act-pair · gemini-2.0-flash

    locally

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     .
    -0.62
    <eos>
    -0.55
    t
    -0.53
     …
    -0.52
    o
    -0.52
    te
    -0.50
     
    -0.50
     of
    -0.50
     in
    -0.50
    y
    -0.49
    POSITIVE LOGITS
     Efq
    1.20
     houſe
    0.98
    BufferException
    0.96
    MigrationBuilder
    0.93
     AspNetCore
    0.90
    تقاوى
    0.89
     $_"
    0.89
     Monfieur
    0.88
     WaitForSeconds
    0.87
     Houſe
    0.87
    Activations Density 0.806%

    No Known Activations