© 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. 10242
    Prev
    Next
    INDEX
    Explanations

    equations and numbers.

    oai_token-act-pair · gemini-2.0-flash

    numbers and calculations

    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
     lies
    -2.19
     lie
    -1.99
     lying
    -1.61
     Lies
    -1.52
    Lying
    -1.51
     lay
    -1.44
     Lying
    -1.42
    Lies
    -1.40
     LIE
    -1.34
     lied
    -1.26
    POSITIVE LOGITS
    ybė
    0.51
     suff
    0.50
     AssemblyCompany
    0.46
    ChildScrollView
    0.46
     Indicates
    0.44
     amputation
    0.43
     encantan
    0.43
     Dort
    0.42
    mittag
    0.42
    кульп
    0.42
    Activations Density 4.343%

    No Known Activations