© 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. 13694
    Prev
    Next
    INDEX
    Explanations

    things related to web pages and layouts or directions

    oai_token-act-pair · gemini-2.0-flash

    phrases related to display options or settings

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

    Document structure/navigation

    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
     front
    -1.39
     back
    -1.35
     rear
    -1.22
     bottom
    -1.19
     left
    -1.18
    front
    -1.17
    back
    -1.13
    bottom
    -1.08
    rear
    -1.03
     top
    -1.00
    POSITIVE LOGITS
    TagMode
    0.57
     to
    0.42
     at
    0.40
     ticking
    0.40
     allem
    0.40
    ук
    0.39
    yna
    0.39
     naar
    0.37
    閱
    0.37
    kanal
    0.36
    Activations Density 2.046%

    No Known Activations