© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5477
    Prev
    Next
    INDEX
    Explanations

    words and short phrases used in technical writing to compare and contrast things

    oai_token-act-pair · gemini-2.0-flash

    random special characters

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

    Technical/legal documents

    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
     purpoſe
    -0.90
     himſelf
    -0.89
     myſelf
    -0.84
     poffible
    -0.84
     Efq
    -0.81
     uſe
    -0.79
     pleaſure
    -0.79
     beſ
    -0.78
     ſtill
    -0.77
     preſent
    -0.76
    POSITIVE LOGITS
    ]")]
    0.56
    aarrggbb
    0.52
    ,}
    0.51
     виправивши
    0.49
    تقاوى
    0.48
    "./
    0.48
    AppMethodBeat
    0.47
     gynhyrchwyd
    0.46
    cipar
    0.46
     himo
    0.45
    Activations Density 3.057%

    No Known Activations