© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14461
    Prev
    Next
    INDEX
    Explanations

    a mix of words related to personal thoughts, colloquial expressions, and possibly non-English words.

    oai_token-act-pair · gemini-2.0-flash

    Informal conversational text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     and
    -0.45
     i
    -0.45
     “
    -0.40
     o
    -0.40
     b
    -0.37
     ri
    -0.36
    .
    -0.35
     so
    -0.34
     प
    -0.34
     sa
    -0.33
    POSITIVE LOGITS
    tagHelperRunner
    1.14
     autorytatywna
    1.10
    yntaxException
    1.09
     propOrder
    1.08
    NameInMap
    1.08
     kaarangay
    1.08
     AssemblyCompany
    1.06
    SharedCtor
    1.06
     חיצוניים
    1.05
     ویکی‌پدی
    1.05
    Activations Density 0.270%

    No Known Activations