© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1894
    Prev
    Next
    INDEX
    Explanations

    action verbs that are about to be done

    oai_token-act-pair · gemini-2.0-flash

    Voicing/Hiding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    BeginContext
    -0.55
    굿
    -0.43
     Meksiku
    -0.42
    pyx
    -0.41
    #
    -0.39
    gmt
    -0.39
     vuotta
    -0.39
    @
    -0.39
    ياة
    -0.38
    uri
    -0.37
    POSITIVE LOGITS
    SourceChecksum
    0.76
     autorytatywna
    0.69
    bootstrapcdn
    0.68
    GenerationType
    0.67
    tagHelperRunner
    0.67
     nakalista
    0.65
     }^{(
    0.64
     kohdetta
    0.62
    jectures
    0.62
     his
    0.62
    Activations Density 3.906%

    No Known Activations