© 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. 11647
    Prev
    Next
    INDEX
    Explanations

    code snippets involving error handling and object properties

    oai_token-act-pair · gemini-2.0-flash

    code errors

    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
    GEBURTSDATUM
    -0.93
    SharedCtor
    -0.83
    Vidite
    -0.79
    ThemeOverlay
    -0.77
     Италијани
    -0.75
    AndEndTag
    -0.75
    IUrlHelper
    -0.71
    UnsafeEnabled
    -0.71
    WireFormat
    -0.69
    OGND
    -0.69
    POSITIVE LOGITS
    GraphicsUnit
    0.69
    gers
    0.47
    коли
    0.47
    anță
    0.46
    ja
    0.46
    sql
    0.44
    ANTO
    0.44
    Erd
    0.44
    rai
    0.43
    icht
    0.43
    Activations Density 10.964%

    No Known Activations