© 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. 8930
    Prev
    Next
    INDEX
    Explanations

    words related to regulations or obligations

    oai_token-act-pair · gemini-2.0-flash

    say "pre"

    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
     before
    -2.75
    before
    -2.45
     Before
    -2.31
    Before
    -2.30
     antes
    -2.03
     sebelum
    -1.98
    BEFORE
    -1.93
     BEFORE
    -1.91
     innan
    -1.66
     voordat
    -1.62
    POSITIVE LOGITS
    pre
    0.62
    Pre
    0.62
     Pre
    0.61
     ujednoznacz
    0.59
    PRE
    0.58
     pre
    0.56
     PRE
    0.56
    toMatchSnapshot
    0.52
    TargetException
    0.52
    AnchorStyles
    0.51
    Activations Density 4.142%

    No Known Activations