© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6715
    Prev
    Next
    INDEX
    Explanations

    relative comparisons of quantities

    oai_token-act-pair · gemini-2.0-flash

    higher

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     higher
    -2.25
    higher
    -2.11
    Higher
    -2.06
     Higher
    -2.02
     HIGHER
    -1.87
     höheren
    -1.45
     höhere
    -1.44
     höher
    -1.37
     högre
    -1.36
     lower
    -1.26
    POSITIVE LOGITS
     المعيارى
    0.63
    makeConstraints
    0.61
    ₤
    0.56
    gbar
    0.53
    PRWEB
    0.53
     NOL
    0.52
    ScopeManager
    0.51
    彿
    0.50
    }{||
    0.50
    TabStop
    0.49
    Activations Density 0.856%

    No Known Activations