© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4146
    Prev
    Next
    INDEX
    Explanations

    a set of very common words such as forms of "to be", conjunctions, and prepositions.

    oai_token-act-pair · gemini-2.0-flash

    negative movie reviews

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

    is/was/are

    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
    WriteBarrier
    -0.65
    ValueStyle
    -0.62
    كويكب
    -0.60
    adpleegd
    -0.59
    WriteTagHelper
    -0.58
    twimg
    -0.56
    ScopeManager
    -0.56
    最快更新
    -0.56
     Fost
    -0.55
     وتسجيلات
    -0.55
    POSITIVE LOGITS
     dreadful
    0.54
     awful
    0.54
     poor
    0.52
     fine
    0.52
     horrible
    0.50
     worst
    0.50
     terrible
    0.50
    awful
    0.49
     wretched
    0.49
     noDo
    0.48
    Activations Density 1.244%

    No Known Activations