© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13937
    Prev
    Next
    INDEX
    Explanations

    the word "the" followed by a noun or adjective.

    oai_token-act-pair · gemini-2.0-flash

    concepts around comparison and advantages

    np_token-act-pair-logits · gpt-4o-mini

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     how
    -0.78
     endregion
    -0.75
    IBOutlet
    -0.74
    AndEndTag
    -0.74
    BeginContext
    -0.65
    endregion
    -0.61
     How
    -0.60
    how
    -0.59
     AssemblyCompany
    -0.56
     Normdatei
    -0.56
    POSITIVE LOGITS
     basics
    0.61
     different
    0.59
     benefits
    0.59
     various
    0.58
     advantages
    0.57
     ins
    0.54
     many
    0.54
     types
    0.54
    的不同
    0.53
     pros
    0.52
    Activations Density 2.070%

    No Known Activations