© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6527
    Prev
    Next
    INDEX
    Explanations

    the word "outer" and sometimes "inner"

    oai_token-act-pair · gemini-2.0-flash

    outer

    np_max-act · gemini-2.0-flash

    outer

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    <bos>
    -1.08
    2
    -0.79
      
    -0.77
    ↵
    -0.77
    1
    -0.74
     
    -0.73
    6
    -0.73
    the
    -0.73
    I
    -0.73
    3
    -0.70
    POSITIVE LOGITS
    ^(@)
    1.39
    ]")]
    1.28
     ContentValues
    1.23
    oredCriteria
    1.15
     itſelf
    1.11
    aarrggbb
    1.09
    ſelf
    1.08
     photolibrary
    1.08
     againſt
    1.07
     himſelf
    1.05
    Activations Density 3.180%

    No Known Activations