Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1239
    Prev
    Next
    INDEX
    Explanations

    technical presentations or descriptions of online videos involving tutorials and webinars

    oai_token-act-pair · gemini-2.0-flash

    Media content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     >=",
    -0.76
     dieux
    -0.69
     vœux
    -0.65
     prisonniers
    -0.65
     betweenstory
    -0.64
     öppna
    -0.61
     imprimée
    -0.58
     ͡°)
    -0.58
    andaag
    -0.57
    }$​
    -0.57
    POSITIVE LOGITS
    tagHelperRunner
    0.57
    mybatisplus
    0.53
    nitz
    0.53
    CreateModel
    0.48
    list
    0.48
     Bache
    0.46
    window
    0.46
    oq
    0.46
     tru
    0.45
    olin
    0.44
    Activations Density 29.605%

    No Known Activations