© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12069
    Prev
    Next
    INDEX
    Explanations

    personal and somewhat abstract poetic or narrative writing

    oai_token-act-pair · gemini-2.0-flash

    nouns related to nature and elements

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

    Creative writing snippets

    np_max-act-logits · gemini-2.0-flash

    articles

    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_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
     sabido
    -0.49
     positivos
    -0.45
     détru
    -0.45
    lewati
    -0.45
    setVerticalGroup
    -0.44
     sedikit
    -0.41
     exteriores
    -0.40
     fermés
    -0.40
    AddHtmlAttribute
    -0.40
    سرائيل
    -0.40
    POSITIVE LOGITS
    queryInterface
    0.81
    NameInMap
    0.79
    SequentialGroup
    0.68
     lakes
    0.67
     blades
    0.67
     waves
    0.67
     moonlight
    0.66
     blade
    0.66
     leaf
    0.65
     lake
    0.65
    Activations Density 5.804%

    No Known Activations