© 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. 583
    Prev
    Next
    INDEX
    Explanations

    numerical data, especially in the context of measurement and statistics

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
    GOTREF
    -0.66
    Geplaatst
    -0.66
     actionTypes
    -0.65
    IsContent
    -0.63
    AnchorStyles
    -0.60
    AndEndTag
    -0.60
    expandindo
    -0.56
    vdots
    -0.55
    ConverterFactory
    -0.55
    inaison
    -0.54
    POSITIVE LOGITS
    9
    0.83
    7
    0.67
    8
    0.65
    6
    0.55
     Ninety
    0.52
    ９
    0.50
    Two
    0.50
     Nine
    0.49
     Seven
    0.48
     ninety
    0.48
    Activations Density 3.780%

    No Known Activations