© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10988
    Prev
    Next
    INDEX
    Explanations

    references to years, or years within a context

    oai_token-act-pair · gemini-2.0-flash

    1800s historical events

    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
     First
    -0.52
     Пер
    -0.47
    First
    -0.47
    po
    -0.45
    처
    -0.45
    Tre
    -0.44
     vorbe
    -0.43
     ze
    -0.43
    flu
    -0.42
     inter
    -0.42
    POSITIVE LOGITS
    ArgsConstructor
    0.83
    RenderAtEndOf
    0.83
     Normdatei
    0.80
    InputTagHelper
    0.73
     كومونز
    0.71
    ChildScrollView
    0.71
    脚注の使い方
    0.71
    istoitu
    0.70
    DebuggerNonUser
    0.69
     AssemblyCulture
    0.69
    Activations Density 1.354%

    No Known Activations