© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3513
    Prev
    Next
    INDEX
    Explanations

    the digit 2 followed by another digit

    oai_token-act-pair · gemini-2.0-flash

    Unicode or special characters

    np_token-act-pair-logits · gpt-4o-mini

    2

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     me
    -0.55
     mit
    -0.54
     An
    -0.54
     an
    -0.53
     a
    -0.49
     Ch
    -0.47
     non
    -0.47
     t
    -0.46
    ↵↵
    -0.46
     n
    -0.46
    POSITIVE LOGITS
    
    1.01
     myſelf
    0.99
     Efq
    0.98
    tvguidetime
    0.97
     للاسماء
    0.96
    ^(@)
    0.96
     itſelf
    0.95
     ―――――
    0.95
     Monfieur
    0.94
    ſelves
    0.89
    Activations Density 2.888%

    No Known Activations