© 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. 6479
    Prev
    Next
    INDEX
    Explanations

    technical writing and scientific articles.

    oai_token-act-pair · gemini-2.0-flash

    specifications

    np_max-act · gemini-2.0-flash
    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
    
    -0.82
    RepeatedField
    -0.79
    ].)
    -0.77
     Theſe
    -0.77
     Monfieur
    -0.76
     déchir
    -0.76
     myſelf
    -0.75
    ."</
    -0.74
    .";
    -0.74
     originalmente
    -0.73
    POSITIVE LOGITS
     Nowadays
    0.56
    Nowadays
    0.56
    }^{+\
    0.53
    VersionUID
    0.50
     advices
    0.49
     defa
    0.48
     belongs
    0.47
    ´
    0.47
     Moreover
    0.47
     estruct
    0.46
    Activations Density 2.488%

    No Known Activations