© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9006
    Prev
    Next
    INDEX
    Explanations

    grammatical constructs such as 'a [noun]', 'is that', and '[noun] [past tense verb]'

    oai_token-act-pair · gemini-2.0-flash

    Formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    setVerticalGroup
    -0.74
     مشين
    -0.71
    出版年
    -0.69
     المعيارى
    -0.63
     semicolon
    -0.62
    WebElementEntity
    -0.61
     pymongo
    -0.61
    laires
    -0.59
     humaine
    -0.57
     Himo
    -0.57
    POSITIVE LOGITS
    <bos>
    2.05
    '
    0.58
    The
    0.53
    Introducing
    0.53
    She
    0.48
    import
    0.48
    ’
    0.47
     discussione
    0.46
     the
    0.45
    <h2>
    0.44
    Activations Density 0.431%

    No Known Activations