© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12369
    Prev
    Next
    INDEX
    Explanations

    words related to observation and knowledge

    oai_token-act-pair · gemini-2.0-flash

    awareness or observation

    np_max-act · gemini-2.0-flash

    noticing

    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_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    migrationBuilder
    -0.59
    interopRequire
    -0.52
     feels
    -0.52
     schaffen
    -0.52
    rieve
    -0.50
    sehen
    -0.50
    unesse
    -0.50
     насеље
    -0.50
    acum
    -0.50
     menghadirkan
    -0.49
    POSITIVE LOGITS
    脚注の使い方
    0.60
    CrossRef
    0.55
     propOrder
    0.52
    CodedInputStream
    0.49
     OMITBAD
    0.48
     pname
    0.48
    ləş
    0.47
    oa̍t
    0.47
     itſelf
    0.47
    ссмо
    0.46
    Activations Density 0.366%

    No Known Activations