© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15766
    Prev
    Next
    INDEX
    Explanations

    references to court cases, legal procedures, and dates

    oai_token-act-pair · gemini-2.0-flash

    9

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    AndEndTag
    -0.78
    \{\\
    -0.63
    三次
    -0.60
    WithTag
    -0.57
     onCancelled
    -0.56
     ninth
    -0.54
    __(/*!
    -0.54
     الرياضيه
    -0.54
     nine
    -0.54
    ineno
    -0.53
    POSITIVE LOGITS
    ⓧ
    0.80
    íí
    0.51
    #+#
    0.48
    Solución
    0.48
     pasirink
    0.47
    });*/
    0.46
    tanleria
    0.44
    ьаж
    0.44
    estias
    0.44
     recién
    0.44
    Activations Density 2.980%

    No Known Activations