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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15429
    Prev
    Next
    INDEX
    Explanations

    mentions of things happening in reality

    oai_token-act-pair · gemini-2.0-flash

    real

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     bershka
    -0.80
     photolibrary
    -0.78
     $_"
    -0.76
    StoryboardSegue
    -0.75
    enderror
    -0.75
     myſelf
    -0.73
     NUKAT
    -0.72
     Theſe
    -0.71
    +#+#
    -0.70
     ―――――
    -0.70
    POSITIVE LOGITS
     proper
    0.54
    実際に
    0.52
     ‘
    0.50
    実際の
    0.49
    ↵↵
    0.47
     '
    0.46
     nyata
    0.46
    <eos>
    0.46
     full
    0.46
     G
    0.46
    Activations Density 1.599%

    No Known Activations