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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10217
    Prev
    Next
    INDEX
    Explanations

    text included with software licenses such as Apache and Copyright

    oai_token-act-pair · gemini-2.0-flash

    articles

    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
    RefNanny
    -0.59
     समीक्षक
    -0.51
    webElement
    -0.50
    Binds
    -0.50
     the
    -0.50
     AttributeSet
    -0.50
    logrus
    -0.50
    ү
    -0.47
    γεν
    -0.47
    findBy
    -0.46
    POSITIVE LOGITS
     isang
    1.09
     a
    1.06
     một
    0.99
     Sebuah
    0.94
     एक
    0.93
     یک
    0.92
     একটি
    0.91
    एक
    0.87
     eine
    0.87
     sebuah
    0.87
    Activations Density 0.303%

    No Known Activations