© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11253
    Prev
    Next
    INDEX
    Explanations

    Japanese words used in debugging or technical support contexts

    oai_token-act-pair · gemini-2.0-flash

    errors and mistakes in code or programming

    np_token-act-pair-logits · gpt-4o-mini

    Programming and XML errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    SOUNDBITE
    -0.62
    ACITY
    -0.57
    izoen
    -0.54
     medel
    -0.53
    giène
    -0.53
     iprot
    -0.52
    bcryptjs
    -0.50
     الدولى
    -0.50
    وافق
    -0.50
    僕も
    -0.49
    POSITIVE LOGITS
    帖最后由
    0.60
    Personendaten
    0.57
     تضيفلها
    0.57
    دانشنامهٔ
    0.54
     GenerationType
    0.53
    Referencias
    0.52
     resourceCulture
    0.51
    Then
    0.50
     estimés
    0.50
    ?
    0.48
    Activations Density 0.700%

    No Known Activations