© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11776
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to ambient temperatures and free stuff

    oai_token-act-pair · gemini-2.0-flash

    experimental conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    WireFormatLite
    -0.60
    bital
    -0.53
     noqa
    -0.52
    <bos>
    -0.52
    bindParam
    -0.52
    lobo
    -0.51
    avir
    -0.49
     mantan
    -0.48
    resten
    -0.48
     obviously
    -0.48
    POSITIVE LOGITS
    DockStyle
    0.70
    AndEndTag
    0.60
     مشين
    0.55
    대로
    0.54
     autorytatywna
    0.53
    awtextra
    0.50
    EndInit
    0.50
     <",
    0.49
     CURIAM
    0.48
    fastjson
    0.47
    Activations Density 0.637%

    No Known Activations