© 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. 3659
    Prev
    Next
    INDEX
    Explanations

    code, perhaps code comments, or code syntax with punctuation, stack traces, or code-related symbols

    oai_token-act-pair · gemini-2.0-flash

    words with special characters or unusual formatting

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

    punctuation

    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
     
    -0.98
     d
    -0.96
     _
    -0.96
     b
    -0.94
     f
    -0.92
     p
    -0.90
     n
    -0.90
     m
    -0.89
     B
    -0.89
     i
    -0.88
    POSITIVE LOGITS
     itſelf
    1.60
     myſelf
    1.45
     Monfieur
    1.40
     Houſe
    1.38
     pleaſure
    1.33
     Anſ
    1.30
     houſe
    1.28
     Reſ
    1.28
     ſtate
    1.26
     ſeveral
    1.24
    Activations Density 1.557%

    No Known Activations