© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10941
    Prev
    Next
    INDEX
    Explanations

    people speaking to one another

    oai_token-act-pair · gemini-2.0-flash

    Someone telling someone something

    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
    #
    -0.58
    glGen
    -0.54
    colgroup
    -0.52
    KOK
    -0.51
     esternos
    -0.51
    PageFactory
    -0.50
    TintMode
    -0.49
    ophore
    -0.49
    CharStream
    -0.48
    wpi
    -0.48
    POSITIVE LOGITS
     that
    0.88
     it
    0.77
     ویکی‌آمباردا
    0.72
     الحره
    0.61
     the
    0.61
     those
    0.61
     about
    0.59
     they
    0.59
     this
    0.58
    ]")]
    0.58
    Activations Density 11.098%

    No Known Activations