© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5970
    Prev
    Next
    INDEX
    Explanations

    words related to boards, councils, institutions, governments

    oai_token-act-pair · gemini-2.0-flash

    organizations or institutions

    np_max-act · gemini-2.0-flash

    organizations

    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_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    %%%%%%%%%%
    -0.58
     monsoon
    -0.49
     нав
    -0.49
     tapasztal
    -0.49
    iläum
    -0.49
     mẽ
    -0.49
    endfor
    -0.48
     prosím
    -0.47
    %%%%%%%%
    -0.47
     hinaus
    -0.47
    POSITIVE LOGITS
     الحره
    0.94
    ScopeManager
    0.91
    出版年
    0.81
    migrationBuilder
    0.80
     تضيفلها
    0.75
     يتيمه
    0.75
    ⓧ
    0.74
     Normdatei
    0.70
    CodeAttribute
    0.69
    GraphicsUnit
    0.69
    Activations Density 1.040%

    No Known Activations