© 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
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12076
    Prev
    Next
    INDEX
    Explanations

    articles of clothing

    oai_token-act-pair · gemini-2.0-flash

    programming terminology

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

    clothing

    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
    lobal
    -0.52
     ring
    -0.45
     Black
    -0.45
    wrt
    -0.45
    INSTANCE
    -0.44
    égio
    -0.43
     arch
    -0.43
     aukš
    -0.41
    Black
    -0.41
     प्रति
    -0.40
    POSITIVE LOGITS
     referenties
    0.76
     onCreateView
    0.68
     saites
    0.67
     <<<<<<<<<<<<<<
    0.66
    contentLoaded
    0.63
    ']>;
    0.63
     psycopg
    0.62
    PhysRev
    0.59
    ỡng
    0.59
     INTERESAR
    0.59
    Activations Density 9.440%

    No Known Activations