© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10505
    Prev
    Next
    INDEX
    Explanations

    items in numbered lists

    oai_token-act-pair · gemini-2.0-flash

    Lists with numbers

    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
    W
    -0.52
     single
    -0.51
    …
    -0.51
     er
    -0.50
     ad
    -0.50
    vée
    -0.48
    w
    -0.48
    arxiv
    -0.48
     W
    -0.48
    vé
    -0.48
    POSITIVE LOGITS
     للمعارف
    0.92
    mybatisplus
    0.90
     Theſe
    0.82
    principalColumn
    0.82
     Efq
    0.81
    ItemBackground
    0.80
    
    0.80
    ThroughAttribute
    0.78
     dépens
    0.77
     Beſ
    0.77
    Activations Density 0.534%

    No Known Activations