© 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. 13062
    Prev
    Next
    INDEX
    Explanations

    content in languages other than English, especially Spanish, Portuguese, French, German and Russian.

    oai_token-act-pair · gemini-2.0-flash

    Non-English language

    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
    <bos>
    -1.23
    webElementXpaths
    -0.85
    invokeLater
    -0.75
    tagHelperRunner
    -0.71
     Савезне
    -0.70
    endphp
    -0.64
     SwitchCompat
    -0.64
    /**
    -0.62
    enumii
    -0.61
    addGap
    -0.59
    POSITIVE LOGITS
     trajets
    0.58
    perative
    0.50
    ruptedException
    0.48
    publicain
    0.48
     Dann
    0.47
     ~=
    0.47
     …
    0.46
    dann
    0.45
     bangles
    0.45
     clowns
    0.44
    Activations Density 1.082%

    No Known Activations