© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11471
    Prev
    Next
    INDEX
    Explanations

    fragments of C++ code related to Windows

    oai_token-act-pair · gemini-2.0-flash

    words with archaic spelling

    np_token-act-pair-logits · gpt-4o-mini

    Archaic spellings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    webElementXpaths
    -0.70
    IVEREF
    -0.60
     Roskov
    -0.58
    RTEE
    -0.54
    Portály
    -0.52
    новниш
    -0.51
     Wikimedijinoj
    -0.48
    ContentAlignment
    -0.48
    Šaltiniai
    -0.46
    WebElementEntity
    -0.46
    POSITIVE LOGITS
     uſed
    0.70
     pleaſure
    0.68
     poffible
    0.68
     ſtre
    0.67
     ſta
    0.66
     ſhe
    0.66
     purpoſe
    0.66
     ſeveral
    0.66
     theſe
    0.65
     Monfieur
    0.65
    Activations Density 0.430%

    No Known Activations