© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14223
    Prev
    Next
    INDEX
    Explanations

    legal or medical jargon within quotes or brackets, and also the word "that" and linking words

    oai_token-act-pair · gemini-2.0-flash

    Legal/medical quotes

    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
     myſelf
    -0.91
     ſeveral
    -0.85
     pleaſure
    -0.82
     itſelf
    -0.82
     themſelves
    -0.82
     himſelf
    -0.80
     Diſ
    -0.79
     ſche
    -0.79
     Egli
    -0.78
     ſtate
    -0.78
    POSITIVE LOGITS
    <bos>
    0.63
    "]))
    0.54
    httphttps
    0.52
     actionMode
    0.51
    >--}}
    0.50
    }],
    0.49
    »։
    0.49
    ")]
    0.49
    ?>">
    0.49
    >|
    0.49
    Activations Density 2.152%

    No Known Activations