© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2950
    Prev
    Next
    INDEX
    Explanations

    text where people discuss what their goals and dreams are and how to make them happen

    oai_token-act-pair · gemini-2.0-flash

    pursuing goals/passions

    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
    Negative Logits
    ReusableCell
    -0.71
     يتيمه
    -0.67
    tagHelperRunner
    -0.66
    DockStyle
    -0.59
    بوابة
    -0.56
    ọa
    -0.54
     Krak
    -0.54
    ISupport
    -0.54
     }}"></
    -0.53
    󠁴
    -0.53
    POSITIVE LOGITS
    FilterChain
    0.71
    AsUp
    0.57
     useContext
    0.53
    VolleyError
    0.52
     career
    0.50
    روت
    0.49
     living
    0.47
     kred
    0.47
    祸
    0.47
     GetEnumerator
    0.47
    Activations Density 3.756%

    No Known Activations