© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12624
    Prev
    Next
    INDEX
    Explanations

    the word "new" or instances of the symbol '{@link'

    oai_token-act-pair · gemini-2.0-flash

    positive words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     ĝ
    -0.45
     AssemblyCulture
    -0.44
     Öff
    -0.44
    abos
    -0.44
    Dear
    -0.44
    sive
    -0.43
     acesso
    -0.43
    까
    -0.42
    Now
    -0.42
    Here
    -0.42
    POSITIVE LOGITS
     оригіналу
    0.73
    ніципа
    0.69
     AspNetCore
    0.68
    esModule
    0.66
    "):
    0.66
    NUMX
    0.65
    Hauptartikel
    0.64
    DebuggerNonUser
    0.62
     sī
    0.60
     AssemblyProduct
    0.59
    Activations Density 1.867%

    No Known Activations