© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5914
    Prev
    Next
    INDEX
    Explanations

    multiple forms of the verb "to be."

    oai_token-act-pair · gemini-2.0-flash

    Descriptive reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     <=",
    -0.66
    SharedCtor
    -0.65
    SharedDtor
    -0.64
    easily
    -0.64
    IndentedString
    -0.62
     Paglinawan
    -0.61
     fácilmente
    -0.59
     nice
    -0.56
     easily
    -0.56
    ніципа
    -0.54
    POSITIVE LOGITS
    Obrázky
    0.63
     surface
    0.54
    ÂN
    0.53
    ity
    0.51
    nextProps
    0.50
     gấp
    0.50
     surfaces
    0.49
    stdafx
    0.49
    stateProvider
    0.48
    Incon
    0.48
    Activations Density 3.431%

    No Known Activations