Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14550
    Prev
    Next
    INDEX
    Explanations

    negations, uncertainty, and inability

    oai_token-act-pair · gemini-2.0-flash

    negation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     المعيارى
    -0.75
    typeorm
    -0.74
    uxxxx
    -0.66
     bezeichneter
    -0.66
    Xna
    -0.65
    IndentedString
    -0.62
    osus
    -0.60
    ImageContext
    -0.60
     onCreateView
    -0.59
    mbggenerated
    -0.58
    POSITIVE LOGITS
     referenties
    0.58
    🏻‍♀️
    0.46
     ruote
    0.45
    Населення
    0.44
    vejec
    0.43
     gelassen
    0.42
     gepf
    0.41
    ์ต
    0.41
    pricht
    0.41
     Meksiku
    0.40
    Activations Density 0.529%

    No Known Activations