© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15361
    Prev
    Next
    INDEX
    Explanations

    parentheses and the letter 'q'.

    oai_token-act-pair · gemini-2.0-flash

    Sts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Amat
    -0.65
    NT
    -0.60
     FT
    -0.58
     LT
    -0.58
    NS
    -0.57
     PSL
    -0.57
    ISL
    -0.57
     NT
    -0.57
    UNT
    -0.57
    MS
    -0.56
    POSITIVE LOGITS
    AntiForgeryToken
    0.60
    FunctionFlags
    0.59
     Sts
    0.56
    stet
    0.54
    sts
    0.54
    Sts
    0.54
     démocr
    0.53
     sts
    0.52
    InstanceState
    0.52
     stazione
    0.51
    Activations Density 1.351%

    No Known Activations