© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 13028
    Prev
    Next
    INDEX
    Explanations

    code snippets, markup formatting, and file separators in source code.

    oai_token-act-pair · gemini-2.0-flash

    horizontal lines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    httphttps
    -0.62
     nakalista
    -0.61
     Metropolitana
    -0.60
    AxisAlignment
    -0.56
    ChromeDriver
    -0.56
    RetentionPolicy
    -0.54
    StructEnd
    -0.52
    numerusform
    -0.52
     coö
    -0.51
     Universitaria
    -0.50
    POSITIVE LOGITS
     typelib
    0.70
     الرياضيه
    0.68
     Normdatei
    0.59
     خارجية
    0.57
    reportWebVitals
    0.55
    arvi
    0.55
    abancı
    0.55
    ranton
    0.55
     HasFactory
    0.54
    ]='\
    0.52
    Activations Density 1.480%

    No Known Activations