© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12886
    Prev
    Next
    INDEX
    Explanations

    code commit information

    oai_token-act-pair · gemini-2.0-flash

    git

    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
    makeConstraints
    -0.85
    ########.
    -0.71
     uParam
    -0.65
     تضيفلها
    -0.61
    writeFieldEnd
    -0.60
     المعيارى
    -0.59
    othed
    -0.58
    ContentValues
    -0.56
    UrlResolution
    -0.55
     LIRE
    -0.55
    POSITIVE LOGITS
    hoeddwyd
    0.69
    AndroidJUnit
    0.69
    <bos>
    0.57
     autorytatywna
    0.56
    Autoritní
    0.53
     Numerade
    0.52
     asas
    0.45
     pää
    0.45
    Σε
    0.44
     tarda
    0.42
    Activations Density 0.686%

    No Known Activations