© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3751
    Prev
    Next
    INDEX
    Explanations

    what seems to be a standard section break and URL citations in academic papers

    oai_token-act-pair · gemini-2.0-flash

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    StoryboardSegue
    -0.88
     mergeFrom
    -0.87
    DockStyle
    -0.86
    CloseOperation
    -0.85
    <bos>
    -0.78
    ngdoc
    -0.77
     htons
    -0.76
    ValueStyle
    -0.73
    FieldBuilder
    -0.71
    djangoproject
    -0.70
    POSITIVE LOGITS
    æl
    0.42
    いか
    0.42
    찮
    0.42
    rrggbb
    0.40
    dol
    0.40
    арт
    0.40
    scryfall
    0.39
    ∉
    0.39
     Again
    0.39
     finely
    0.38
    Activations Density 8.453%

    No Known Activations