© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14055
    Prev
    Next
    INDEX
    Explanations

    large empty spaces, newlines, formatting issues, or other artifacts of unstructured data

    oai_token-act-pair · gemini-2.0-flash

    code/technical snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     GenerationType
    -0.68
    TemporalType
    -0.68
    medades
    -0.60
    IBar
    -0.55
    xaml
    -0.54
    PHeader
    -0.54
    ctrons
    -0.54
    glGen
    -0.52
    routeProvider
    -0.52
    ExecuteReader
    -0.50
    POSITIVE LOGITS
    <bos>
    1.12
    downarrow
    0.51
     engagé
    0.50
     мѣ
    0.50
    DebuggerStep
    0.50
     kasarigan
    0.48
    RegistryLite
    0.48
    ifrance
    0.48
     WALTZ
    0.48
    Gambas
    0.48
    Activations Density 2.509%

    No Known Activations