© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9062
    Prev
    Next
    INDEX
    Explanations

    general use prepositions and articles of speech

    oai_token-act-pair · gemini-2.0-flash

    concepts of change and competitiveness

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

    constant change

    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
    ConstraintMaker
    -0.61
     استنادى
    -0.56
    èze
    -0.54
    Ví
    -0.53
    ApiModel
    -0.53
    standing
    -0.53
     binh
    -0.53
     Erle
    -0.52
    ekte
    -0.52
    RunWith
    -0.52
    POSITIVE LOGITS
     changing
    0.97
     Changing
    0.82
    changing
    0.81
     ever
    0.76
    Changing
    0.76
     uncertain
    0.75
     fast
    0.74
     changed
    0.67
    changed
    0.66
     competitive
    0.65
    Activations Density 1.450%

    No Known Activations