© 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. 9585
    Prev
    Next
    INDEX
    Explanations

    uses of the word "be" and related words such as "is", "was" and "will."

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "rest"

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

    starts with "re"

    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
     AssemblyTitle
    -0.66
     autorytatywna
    -0.64
     cdti
    -0.59
     DBNull
    -0.58
     <=",
    -0.58
     Stok
    -0.57
     Insertion
    -0.57
    SourceChecksum
    -0.57
     itſelf
    -0.56
     ioutil
    -0.56
    POSITIVE LOGITS
     rest
    1.30
     Rest
    1.08
    rest
    1.03
    Rest
    1.01
     res
    0.99
     rec
    0.99
     Res
    0.98
     re
    0.93
     ref
    0.91
     resta
    0.91
    Activations Density 2.296%

    No Known Activations