© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13938
    Prev
    Next
    INDEX
    Explanations

    clinical studies with numerical data and some accompanying context words like "with", "from", "per", parenthesis, and other bracketing characters

    oai_token-act-pair · gemini-2.0-flash

    Statistical data and percentages

    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
    oredCriteria
    -1.02
    :✨
    -0.82
    ResumeLayout
    -0.73
    Datuak
    -0.71
     صوتيه
    -0.71
    Hauptartikel
    -0.70
     betweenstory
    -0.69
    sizeCache
    -0.67
     resourceCulture
    -0.66
    #+#
    -0.66
    POSITIVE LOGITS
    nextProps
    0.45
    Schedulers
    0.45
    table
    0.35
     Verf
    0.35
    idic
    0.34
    Wid
    0.34
    烈
    0.32
     eva
    0.31
    šlo
    0.31
     numberOfRows
    0.31
    Activations Density 23.290%

    No Known Activations