© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16033
    Prev
    Next
    INDEX
    Explanations

    a sequence of words related to finishing or achieving a task

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    AndEndTag
    -0.78
     EconPapers
    -0.77
     kasarigan
    -0.73
    NegativeButton
    -0.72
     isInitialized
    -0.70
    Personendaten
    -0.69
    ंदीखरीदारी
    -0.68
    ScopeManager
    -0.65
     JpaRepository
    -0.64
     transférez
    -0.63
    POSITIVE LOGITS
    zość
    0.51
    řevě
    0.49
     liggen
    0.49
    繞
    0.47
    autoIncrement
    0.47
    laught
    0.46
    angliski
    0.45
    Étymologie
    0.45
    likle
    0.44
    jectures
    0.44
    Activations Density 0.856%

    No Known Activations