© 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. 10428
    Prev
    Next
    INDEX
    Explanations

    articles followed by adjectives

    oai_token-act-pair · gemini-2.0-flash

    a

    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
    ط
    -0.46
     lyd
    -0.43
     stø
    -0.42
     viktigt
    -0.40
     regionales
    -0.40
    ির
    -0.40
     bizony
    -0.39
    безпе
    -0.39
    人
    -0.39
     mon
    -0.39
    POSITIVE LOGITS
     AssemblyCompany
    1.09
    LookAnd
    1.05
     <=",
    1.00
    bootstrapcdn
    1.00
     bezeichneter
    0.95
     onAnimation
    0.92
    AccessorTable
    0.90
    rungsseite
    0.89
    GOTREF
    0.88
    PreferredItem
    0.88
    Activations Density 1.249%

    No Known Activations