© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13373
    Prev
    Next
    INDEX
    Explanations

    phrases enclosed in quotation marks

    oai_token-act-pair · gemini-2.0-flash

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     R
    -0.46
     P
    -0.46
    味
    -0.42
     s
    -0.42
     B
    -0.41
    et
    -0.41
    jons
    -0.41
    джан
    -0.40
     _
    -0.40
    ...
    -0.40
    POSITIVE LOGITS
     للمعارف
    0.96
     myſelf
    0.85
     Monfieur
    0.81
     itſelf
    0.80
     Efq
    0.77
     becauſe
    0.75
    ніципалі
    0.75
     дописавши
    0.74
    RunAsync
    0.73
     ſeveral
    0.72
    Activations Density 0.156%

    No Known Activations