© 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
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 312
    Prev
    Next
    INDEX
    Explanations

    phrases related to identification, whether it be biological or otherwise

    oai_token-act-pair · gemini-2.0-flash

    identity, signature

    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
     AttributeSet
    -0.97
    AndEndTag
    -0.87
    脚注の使い方
    -0.87
    sidemargin
    -0.75
    uesia
    -0.73
    numerusform
    -0.71
    DockStyle
    -0.68
     pleaſure
    -0.68
    aarrggbb
    -0.68
    AccessFile
    -0.68
    POSITIVE LOGITS
     distinctive
    0.47
     look
    0.45
     charakterysty
    0.41
     continúas
    0.41
     peças
    0.41
     Look
    0.41
     distinguishing
    0.40
     feature
    0.40
     fiables
    0.40
     );
    
    0.39
    Activations Density 1.503%

    No Known Activations