© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7762
    Prev
    Next
    INDEX
    Explanations

    code snippets involving tags, blocks, and identifiers

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    +#+#
    -0.70
     ویکی‌پدیا
    -0.67
     الرياضيه
    -0.66
     dedo
    -0.66
    o
    -0.58
    ServiceModel
    -0.57
    ウザ
    -0.57
     ऑ
    -0.56
     оригіналу
    -0.55
     findViewById
    -0.55
    POSITIVE LOGITS
     vectorielle
    0.64
    perity
    0.60
    fulness
    0.60
    },[])
    0.59
    مقاله
    0.58
     isComment
    0.57
     CreateTagHelper
    0.56
    izacja
    0.56
    ressee
    0.56
    ruptcy
    0.56
    Activations Density 0.939%

    No Known Activations