© 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. 11838
    Prev
    Next
    INDEX
    Explanations

    strings of tokens in boilerplate advertisement copy

    oai_token-act-pair · gemini-2.0-flash

    Product technical descriptions

    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
    клопе
    -0.65
    tagHelperRunner
    -0.64
     Ror
    -0.59
    ilter
    -0.59
     Jefus
    -0.59
    EndInit
    -0.58
    viewWillAppear
    -0.58
     ་་
    -0.57
    complexType
    -0.57
     UITableViewCell
    -0.57
    POSITIVE LOGITS
     viento
    0.47
    AVES
    0.47
     wind
    0.46
     ISNI
    0.45
    økt
    0.45
     apellidos
    0.43
    جغرافيا
    0.42
    Diwedd
    0.42
    dym
    0.42
     K
    0.41
    Activations Density 0.305%

    No Known Activations