© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11359
    Prev
    Next
    INDEX
    Explanations

    things located in a particular area of the American Midwest

    oai_token-act-pair · gemini-2.0-flash

    Dakota/Nile

    np_max-act · gemini-2.0-flash

    place names

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     kasarigan
    -0.59
    downe
    -0.59
    istocene
    -0.57
     bites
    -0.56
    enteuer
    -0.56
     Chiu
    -0.55
     بيها
    -0.54
    ].(
    -0.52
     mô
    -0.49
    skap
    -0.48
    POSITIVE LOGITS
    InjectAttribute
    1.07
    tvguidetime
    0.83
    KommentareTeilen
    0.72
     noDo
    0.69
    UnusedPrivate
    0.68
    +#+#
    0.65
    providedIn
    0.61
     فريبيس
    0.61
    awtextra
    0.61
    adaptiveStyles
    0.60
    Activations Density 0.637%

    No Known Activations