© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3376
    Prev
    Next
    INDEX
    Explanations

    years in the 1900s, possibly with an imperfect OCR recognition of the digit "1"

    oai_token-act-pair · gemini-2.0-flash

    years and dates

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     dile
    -0.58
     تضيفلها
    -0.52
     consultato
    -0.52
     vale
    -0.49
     umat
    -0.49
    roglo
    -0.48
    迫
    -0.47
    tenis
    -0.47
    verser
    -0.47
    pagn
    -0.46
    POSITIVE LOGITS
     BorderRadius
    0.76
    ⓧ
    0.72
    ########.
    0.71
    #+#
    0.71
    Controllo
    0.65
    참고
    0.63
    UnusedPrivate
    0.61
    InitVars
    0.61
    ANTLR
    0.59
     AssemblyTitle
    0.59
    Activations Density 0.576%

    No Known Activations