© 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
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10132
    Prev
    Next
    INDEX
    Explanations

    program or specification code

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    thâu
    -0.76
    PerformLayout
    -0.60
     vPvB
    -0.57
    MockMvc
    -0.56
     BoxFit
    -0.54
    WebElementEntity
    -0.52
    exitRule
    -0.52
    GIVEREF
    -0.51
    __':
    -0.48
    AndEndTag
    -0.47
    POSITIVE LOGITS
     Вікіпе
    0.60
     Wikimédia
    0.57
    بوابة
    0.55
    Andra
    0.51
     pertumbuhan
    0.49
    GraphicsUnit
    0.48
    acin
    0.47
    Portale
    0.46
    latform
    0.46
    refour
    0.46
    Activations Density 3.734%

    No Known Activations