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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5114
    Prev
    Next
    INDEX
    Explanations

    text inside of single quotes

    oai_token-act-pair · gemini-2.0-flash

    quotation marks and apostrophes

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

    opening quotes

    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
     "
    -1.28
     “
    -1.16
     «
    -1.10
     „
    -0.95
     ''
    -0.81
    「
    -0.78
     ``
    -0.76
     ‘‘
    -0.71
     「
    -0.66
     "/
    -0.66
    POSITIVE LOGITS
    …’
    0.76
     Shakspeare
    0.76
    ...'
    0.73
     Cæsar
    0.73
    .”)
    0.73
     poffe
    0.72
     reaſon
    0.72
     auffi
    0.72
     Majefty
    0.71
    ...")
    0.70
    Activations Density 2.037%

    No Known Activations