© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11349
    Prev
    Next
    INDEX
    Explanations

    a variety of words that could be related to opinions or discussions

    oai_token-act-pair · gemini-2.0-flash

    words related to categorization or classifications

    np_token-act-pair-logits · gpt-4o-mini
    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
    Erreferentziak
    -0.89
     الحره
    -0.73
     EconPapers
    -0.72
     surla
    -0.71
     TestBed
    -0.68
    NewUrlParser
    -0.66
     NgModule
    -0.65
    ManagedBean
    -0.65
     useStyles
    -0.65
    __()
    -0.64
    POSITIVE LOGITS
     peri
    0.45
    teria
    0.44
    RegExp
    0.43
     AssemblyTitle
    0.43
    permalink
    0.42
    heav
    0.40
    ền
    0.40
    atko
    0.39
     RegExp
    0.37
    hells
    0.37
    Activations Density 5.507%

    No Known Activations