© 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. 3451
    Prev
    Next
    INDEX
    Explanations

    somewhat arbitrarily words that are preceded or followed by other words.

    oai_token-act-pair · gemini-2.0-flash

    have

    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
     onAnimation
    -0.68
    ContentAsync
    -0.60
    omock
    -0.59
    aarrggbb
    -0.58
     MonoBehaviour
    -0.55
    printStackTrace
    -0.53
     StatelessWidget
    -0.53
    Ể
    -0.52
    ">—
    -0.51
    RegressionTest
    -0.50
    POSITIVE LOGITS
     had
    2.11
     have
    1.96
     Have
    1.91
    Have
    1.88
    have
    1.86
     having
    1.84
    Had
    1.78
    had
    1.76
     Had
    1.74
     HAVE
    1.62
    Activations Density 2.629%

    No Known Activations