© 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. 11730
    Prev
    Next
    INDEX
    Explanations

    locations, organizations, and errors.

    oai_token-act-pair · gemini-2.0-flash

    code and technical text

    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
    XmlAccessType
    -0.56
    RetentionPolicy
    -0.56
     GenerationType
    -0.54
    TableHead
    -0.49
    routeProvider
    -0.47
    ])).
    -0.46
    AsyncResult
    -0.45
    AuthContext
    -0.45
    itecture
    -0.44
    ModelBuilder
    -0.44
    POSITIVE LOGITS
     autorytatywna
    0.71
     Roskov
    0.65
    WEBPACK
    0.61
    +#+#
    0.60
    Autoritní
    0.59
    abestanden
    0.59
    vician
    0.56
     Dominant
    0.54
    WriteTagHelper
    0.54
     disponibilités
    0.54
    Activations Density 0.059%

    No Known Activations