© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10278
    Prev
    Next
    INDEX
    Explanations

    code snippets using a variety of languages and formats

    oai_token-act-pair · gemini-2.0-flash

    Code and data structures

    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
     *>(
    -0.48
    lieved
    -0.48
    WriteBarrier
    -0.47
    varu
    -0.47
     py
    -0.47
    )\}$
    -0.47
    ])));
    -0.46
    Batal
    -0.46
    ejb
    -0.46
     ص
    -0.45
    POSITIVE LOGITS
    djangoproject
    0.66
    EndContext
    0.57
    تقاوى
    0.54
     Daarom
    0.54
     PeEnEo
    0.54
    цездатний
    0.54
     unknownFields
    0.54
    omitempty
    0.52
     autorytatywna
    0.51
    ieteur
    0.51
    Activations Density 0.768%

    No Known Activations