© 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. 11796
    Prev
    Next
    INDEX
    Explanations

    pronouns and other words used to refer to people and groups of people, especially associated with events, reporting, or officialdom.

    oai_token-act-pair · gemini-2.0-flash

    various forms of 'had'

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

    had

    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
     cherchés
    -0.78
    MessageTagHelper
    -0.63
     مرئيه
    -0.60
    stateProvider
    -0.59
    FieldBuilder
    -0.58
    apunov
    -0.57
    AsUp
    -0.57
     EdgeInsets
    -0.56
    تقاوى
    -0.56
     nahilalakip
    -0.55
    POSITIVE LOGITS
     had
    2.97
    Had
    2.53
     Had
    2.47
    had
    2.47
     HAD
    2.05
     hadden
    1.73
     hadde
    1.71
     hatte
    1.70
     hatten
    1.69
     había
    1.65
    Activations Density 3.739%

    No Known Activations