© 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. 11739
    Prev
    Next
    INDEX
    Explanations

    capitalized proper nouns, especially names of people and organizations

    oai_token-act-pair · gemini-2.0-flash

    research/technical texts

    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
     propOrder
    -0.66
    EnableWeb
    -0.66
    UserScript
    -0.66
    .*")]
    -0.64
    AndroidJUnit
    -0.62
     Diſ
    -0.60
     onAnimation
    -0.59
    +:+
    -0.59
     становника
    -0.58
    XmlAccessType
    -0.57
    POSITIVE LOGITS
    ObjectModel
    0.51
    AndEndTag
    0.50
    PyExc
    0.48
     كومونز
    0.47
    rebro
    0.47
     actifs
    0.46
    Activity
    0.44
     Sek
    0.44
     activos
    0.44
     activity
    0.44
    Activations Density 0.207%

    No Known Activations