© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 4755
    Prev
    Next
    INDEX
    Explanations

    first person pronouns, especially 'I', in sentences with qualifying language

    oai_token-act-pair · gemini-2.0-flash

    tags or programming concepts

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

    Forums/blogs text

    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
     isn
    -0.83
     aren
    -0.73
    Is
    -0.71
     doesn
    -0.68
     wasn
    -0.63
     isnt
    -0.63
    isn
    -0.61
     wouldn
    -0.60
    don
    -0.60
     shouldn
    -0.59
    POSITIVE LOGITS
    #+#
    1.02
    AddTagHelper
    0.97
    Personendaten
    0.94
     @"/
    0.91
     Савезне
    0.91
     disambiguazione
    0.88
    曖昧さ回避
    0.87
     CreateTagHelper
    0.86
    脚注の使い方
    0.86
    NameInMap
    0.85
    Activations Density 2.381%

    No Known Activations