© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8130
    Prev
    Next
    INDEX
    Explanations

    small words such as prepositions and articles, especially when appearing together

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Lightboxes
    -0.73
     initComponents
    -0.60
     Olympedia
    -0.60
    WebServlet
    -0.60
    EDEFAULT
    -0.58
     protoimpl
    -0.57
     للاسماء
    -0.57
     iprot
    -0.56
    OCCURRED
    -0.56
     كومونز
    -0.56
    POSITIVE LOGITS
    TagName
    0.47
     canadienne
    0.46
    man
    0.46
    aboo
    0.46
    ABIL
    0.44
    boBox
    0.43
    nought
    0.43
     Baths
    0.42
     COAL
    0.42
    льності
    0.42
    Activations Density 2.354%

    No Known Activations