© 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. 11403
    Prev
    Next
    INDEX
    Explanations

    sentences describing a difficult experience

    oai_token-act-pair · gemini-2.0-flash

    terms related to stress

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

    stress

    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
     فريبيس
    -0.54
    MENAFN
    -0.53
     possible
    -0.52
    ódnica
    -0.52
    EFIAPI
    -0.52
    possible
    -0.51
     الرياضيه
    -0.50
    賓
    -0.50
    CppCodeGen
    -0.49
    Allowed
    -0.49
    POSITIVE LOGITS
     stressful
    0.61
    featureID
    0.56
     STRESS
    0.55
     onOptions
    0.51
     setCode
    0.50
    DockStyle
    0.49
    argout
    0.49
    iastes
    0.47
     menyeb
    0.47
     Stress
    0.47
    Activations Density 1.277%

    No Known Activations