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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9767
    Prev
    Next
    INDEX
    Explanations

    XML parameters and other code-like syntax

    oai_token-act-pair · gemini-2.0-flash

    param

    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
    LookAnd
    -0.93
     متعلقه
    -0.88
     esternos
    -0.84
    ScopeManager
    -0.80
     tartalomajánló
    -0.79
     GenerationType
    -0.79
     Wiktionnaire
    -0.78
     AssemblyCompany
    -0.77
    хьтан
    -0.76
     препратки
    -0.76
    POSITIVE LOGITS
     
    0.69
    <eos>
    0.51
    ↵↵
    0.47
     with
    0.44
     at
    0.44
    ense
    0.43
    ne
    0.43
    ↵
    0.41
    with
    0.41
     @
    0.40
    Activations Density 1.944%

    No Known Activations