© 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. 8540
    Prev
    Next
    INDEX
    Explanations

    the word "unique" and words indicating exceptions

    oai_token-act-pair · gemini-2.0-flash

    unique

    np_max-act · gemini-2.0-flash

    unique

    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
    RenderAtEndOf
    -0.63
    complexContent
    -0.61
    abetes
    -0.61
    protoimpl
    -0.59
     lópez
    -0.59
     rodríguez
    -0.58
     gonzález
    -0.57
     kleid
    -0.54
    dersfield
    -0.53
    rrggbb
    -0.52
    POSITIVE LOGITS
    traction
    0.77
    onesi
    0.75
    phonic
    0.71
    큰
    0.71
    Rüyada
    0.71
    ificantly
    0.68
    ISM
    0.65
     Floors
    0.65
    merci
    0.64
     tapp
    0.64
    Activations Density 1.045%

    No Known Activations