© 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. 10470
    Prev
    Next
    INDEX
    Explanations

    numerical data and variable assignments

    oai_token-act-pair · gemini-2.0-flash

    =. It finds the equals sign

    np_max-act-logits · gemini-2.0-flash

    say "digits"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     sixth
    -0.85
     Six
    -0.82
     seventh
    -0.81
    6
    -0.75
     SIX
    -0.75
    六
    -0.74
     Sixth
    -0.74
     six
    -0.74
    Sixth
    -0.73
     Seven
    -0.72
    POSITIVE LOGITS
    inaison
    0.59
    CloseOperation
    0.58
     Evol
    0.57
    principalColumn
    0.57
     Мексичка
    0.57
    RenderAtEndOf
    0.56
    rativa
    0.55
     '@/
    0.52
    INCT
    0.48
    PreferredItem
    0.48
    Activations Density 1.650%

    No Known Activations