© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12153
    Prev
    Next
    INDEX
    Explanations

    technical papers and uses the word "instance" in quoted citations of a source

    oai_token-act-pair · gemini-2.0-flash

    instance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     fufficient
    -0.53
     neceff
    -0.51
    cabul
    -0.50
     Kirsch
    -0.50
     guarantee
    -0.50
     sphinct
    -0.49
    ఓ
    -0.48
     Guaranteed
    -0.47
     Guarantee
    -0.46
     Protocols
    -0.46
    POSITIVE LOGITS
    Например
    0.81
     примеру
    0.80
    říklad
    0.80
     např
    0.78
    tvguidetime
    0.77
    rinfo
    0.75
    например
    0.73
     bijvoorbeeld
    0.71
     třeba
    0.70
     MainAxisSize
    0.69
    Activations Density 1.501%

    No Known Activations