© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8751
    Prev
    Next
    INDEX
    Explanations

    Java code

    oai_token-act-pair · gemini-2.0-flash

    min/max

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     StatelessWidget
    -0.71
    <bos>
    -0.66
    uxxxx
    -0.63
    awtextra
    -0.59
     mapStateToProps
    -0.55
     getIntent
    -0.54
    flashdata
    -0.54
    "
    -0.53
     Parigi
    -0.53
    '
    -0.52
    POSITIVE LOGITS
    Diwedd
    0.66
     الحره
    0.58
    TagMode
    0.57
    Tembelea
    0.56
    دانشنامهٔ
    0.54
    tagHelperRunner
    0.54
     Wiktionnaire
    0.54
    liculas
    0.52
     سكانية
    0.52
    +:+
    0.51
    Activations Density 2.683%

    No Known Activations