© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5450
    Prev
    Next
    INDEX
    Explanations

    mentions of well-being or importance.

    oai_token-act-pair · gemini-2.0-flash

    lives and likes

    np_max-act · gemini-2.0-flash

    say "of"

    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
     ujednoznacz
    -1.16
     ſmall
    -1.05
     purpoſe
    -1.00
     whoſe
    -0.97
    SequentialGroup
    -0.97
    OGND
    -0.93
     leſs
    -0.92
     ſind
    -0.91
    ^(@)
    -0.90
    abestanden
    -0.90
    POSITIVE LOGITS
    '
    0.68
    ↵↵
    0.58
    a
    0.55
     
    0.54
     of
    0.54
    ’
    0.52
    ↵
    0.52
    føre
    0.50
     was
    0.48
    "
    0.48
    Activations Density 1.430%

    No Known Activations