© 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. 12250
    Prev
    Next
    INDEX
    Explanations

    the Greek symbol "nu" in mathematical formulas

    oai_token-act-pair · gemini-2.0-flash

    nu

    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
     helped
    -1.14
     Helped
    -1.01
    helped
    -0.96
     aided
    -0.73
     taught
    -0.69
     supported
    -0.67
     assisted
    -0.66
     enabled
    -0.66
     aidé
    -0.65
     Taught
    -0.64
    POSITIVE LOGITS
    prefixer
    0.73
    บัติ
    0.67
    )|^{
    0.59
    chließ
    0.59
     HasFactory
    0.58
    φων
    0.57
    geois
    0.57
    %")
    0.57
    EndContext
    0.56
    曖昧さ回避
    0.56
    Activations Density 3.774%

    No Known Activations