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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11807
    Prev
    Next
    INDEX
    Explanations

    phrases and words often found in books and articles, and also some words related to food.

    oai_token-act-pair · gemini-2.0-flash

    Quotes and legal language

    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
     ویکی‌پدیا
    -0.91
    setVerticalGroup
    -0.90
     Daß
    -0.84
     متعلقه
    -0.83
    uxxxx
    -0.83
     MotionEvent
    -0.83
     Moslem
    -0.83
    ConstraintMaker
    -0.82
     estekak
    -0.81
     دیکھیے
    -0.80
    POSITIVE LOGITS
    TLDR
    0.54
     impactful
    0.50
     ($
    0.49
    prisingly
    0.47
    Lastly
    0.47
    Alright
    0.47
     siguran
    0.47
    Additionally
    0.46
    Welp
    0.46
     underwhelming
    0.46
    Activations Density 2.378%

    No Known Activations