© 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. 11243
    Prev
    Next
    INDEX
    Explanations

    words that describe an attribute or emotion

    oai_token-act-pair · gemini-2.0-flash

    descriptions and opinions

    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
     far
    -0.49
     prop
    -0.48
     OFDb
    -0.46
    mybatisplus
    -0.46
    !*\
    -0.45
    hind
    -0.44
     cross
    -0.43
     MenuView
    -0.42
     with
    -0.42
     iprot
    -0.42
    POSITIVE LOGITS
     pleaſure
    0.78
     loue
    0.67
     fevere
    0.66
     Absol
    0.65
     ſever
    0.65
     itſelf
    0.65
     reaſon
    0.64
     الحره
    0.63
     purpoſe
    0.63
     faſt
    0.62
    Activations Density 1.864%

    No Known Activations