© 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. 14082
    Prev
    Next
    INDEX
    Explanations

    code, statistics, or group comparison in research

    oai_token-act-pair · gemini-2.0-flash

    Code/data group or type

    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
    ̀
    -0.43
    ebenarnya
    -0.42
     Bes
    -0.41
    Specifiche
    -0.41
    ROIT
    -0.40
    CardBody
    -0.40
    humanité
    -0.39
    tamin
    -0.39
    Ɛ
    -0.38
    mucho
    -0.38
    POSITIVE LOGITS
     CreateTagHelper
    0.83
    Tikang
    0.75
     useAppContext
    0.75
    ModelAdmin
    0.72
    Espèce
    0.71
    <bos>
    0.70
    новниш
    0.69
    GOTREF
    0.68
    下载附件
    0.68
    ModelSerializer
    0.67
    Activations Density 4.633%

    No Known Activations