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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3332
    Prev
    Next
    INDEX
    Explanations

    snippets of code and words in languages other than English, especially Portuguese and Serbo-Croatian

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     is
    -1.24
     are
    -1.03
     has
    -0.99
     was
    -0.86
     will
    -0.81
     contains
    -0.81
     would
    -0.72
     bestaat
    -0.71
    的是
    -0.71
     can
    -0.70
    POSITIVE LOGITS
    Hochspringen
    0.66
    Havolalar
    0.60
     AssemblyProduct
    0.58
     "..\..\..\
    0.57
    cinia
    0.57
    المناصب
    0.56
    transQ
    0.56
     himo
    0.55
     Downloader
    0.53
    #+#
    0.53
    Activations Density 1.295%

    No Known Activations