© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10804
    Prev
    Next
    INDEX
    Explanations

    the word "arrow" and the tags beginning with the word "Text"

    oai_token-act-pair · gemini-2.0-flash

    arrow

    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
    :✨
    -0.98
     الحره
    -0.94
     EconPapers
    -0.88
     demurrer
    -0.85
     Melch
    -0.85
    EndInit
    -0.85
     instantiation
    -0.84
     nakalista
    -0.82
    ArgumentParser
    -0.81
     optimisation
    -0.80
    POSITIVE LOGITS
     for
    0.67
    a
    0.65
     down
    0.60
     in
    0.59
     to
    0.57
    s
    0.57
     than
    0.56
     is
    0.55
     at
    0.55
     not
    0.54
    Activations Density 0.680%

    No Known Activations