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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14523
    Prev
    Next
    INDEX
    Explanations

    passages that express the idea of hope and political action

    oai_token-act-pair · gemini-2.0-flash

    activism, organizing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     BorderRadius
    -0.48
     للتو
    -0.46
    脚注の使い方
    -0.44
    rdı
    -0.43
     ás
    -0.41
    oren
    -0.40
     gim
    -0.39
    الإنجليزية
    -0.38
     bereit
    -0.38
    ню
    -0.38
    POSITIVE LOGITS
    etCode
    0.69
    ChildScrollView
    0.68
    Tracce
    0.67
     onPostExecute
    0.67
     crdi
    0.66
    rawDesc
    0.66
    ]")]
    0.65
    babwe
    0.65
    WithIOException
    0.63
    
    0.63
    Activations Density 2.986%

    No Known Activations