© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7708
    Prev
    Next
    INDEX
    Explanations

    uses of the word "somewhat", sometimes with words related to expertise or specialization

    oai_token-act-pair · gemini-2.0-flash

    somewhat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    yarnpkg
    -0.71
    AndEndTag
    -0.68
    bootstrapcdn
    -0.63
     démocr
    -0.63
     Nacionales
    -0.61
    AutoresizingMask
    -0.61
     femininas
    -0.60
     समीक्षाएं
    -0.59
     citoyens
    -0.58
     dourada
    -0.58
    POSITIVE LOGITS
    üyada
    0.88
    WebControls
    0.81
     Paglinawan
    0.71
    TagMode
    0.70
    azol
    0.68
     Ressource
    0.64
    ferous
    0.64
     jScrollPane
    0.64
    redientes
    0.63
     Meksiku
    0.63
    Activations Density 1.491%

    No Known Activations