© 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. 12362
    Prev
    Next
    INDEX
    Explanations

    product descriptions containing conjunctions, and exclamation points within a sentence

    oai_token-act-pair · 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
     aile
    -0.56
     apie
    -0.49
     Ottobre
    -0.49
     orice
    -0.47
     apro
    -0.45
     innocence
    -0.45
    setCellValue
    -0.44
     otherwise
    -0.44
     about
    -0.44
     Micho
    -0.44
    POSITIVE LOGITS
    UserScript
    0.83
    DockStyle
    0.82
     يتيمه
    0.76
     مرئيه
    0.73
    SourceChecksum
    0.70
    ThroughAttribute
    0.69
    OGND
    0.69
    TagMode
    0.68
    WebVitals
    0.68
    Amicalement
    0.67
    Activations Density 2.761%

    No Known Activations