© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16075
    Prev
    Next
    INDEX
    Explanations

    lists of things, often connected by "and"

    oai_token-act-pair · gemini-2.0-flash

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    IsContent
    -0.61
    
    -0.59
    |$.
    -0.52
     Different
    -0.52
     ():
    -0.52
    出版年
    -0.51
    ILayout
    -0.50
    الحياه
    -0.50
    Vidite
    -0.49
    stateProvider
    -0.48
    POSITIVE LOGITS
     many
    1.98
    many
    1.78
     much
    1.72
    much
    1.54
     muitos
    1.48
    Many
    1.48
     muchos
    1.48
     MANY
    1.46
     muchas
    1.42
    MANY
    1.40
    Activations Density 2.246%

    No Known Activations