© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10562
    Prev
    Next
    INDEX
    Explanations

    words of importance that have an emotional component

    oai_token-act-pair · gemini-2.0-flash

    abstract concepts/qualities

    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
    :✨
    -0.66
     eyel
    -0.63
    processable
    -0.63
     <=",
    -0.61
    CPtr
    -0.60
    pherals
    -0.57
    QRST
    -0.57
    ">//
    -0.56
    +#+#
    -0.56
    Datuak
    -0.55
    POSITIVE LOGITS
    RefreshLayout
    0.60
     BoxDecoration
    0.52
    ednesdays
    0.50
    TouchListener
    0.49
    endroit
    0.48
    jenige
    0.47
    Manbalar
    0.47
     of
    0.46
    يرا
    0.45
     հղումներ
    0.44
    Activations Density 2.211%

    No Known Activations