© 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. 5823
    Prev
    Next
    INDEX
    Explanations

    the word "quite"

    oai_token-act-pair · gemini-2.0-flash

    quite

    np_max-act · gemini-2.0-flash

    quite

    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
     purpoſe
    -1.54
     ſtate
    -1.48
     Monfieur
    -1.41
     Jefus
    -1.35
     Diſ
    -1.35
     ſche
    -1.30
     ſeveral
    -1.30
     pleaſure
    -1.30
     Anſ
    -1.27
     Inſ
    -1.27
    POSITIVE LOGITS
    ]',
    0.75
     a
    0.73
    ⁩
    0.72
    ''')
    0.70
     the
    0.69
    ciutto
    0.69
     re
    0.69
     major
    0.68
     in
    0.67
    */,
    0.67
    Activations Density 2.327%

    No Known Activations