© 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. 11801
    Prev
    Next
    INDEX
    Explanations

    terms related to dimensions, realms and worlds

    oai_token-act-pair · gemini-2.0-flash

    terms related to dimensions or planes

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

    plane

    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
    ########.
    -0.71
    NUMX
    -0.71
    Искәрмәләр
    -0.68
    StoryboardSegue
    -0.67
    ArgsConstructor
    -0.66
    didSet
    -0.66
    tagHelperRunner
    -0.66
    +/**
    -0.66
    PyExc
    -0.64
    AndEndTag
    -0.63
    POSITIVE LOGITS
     plane
    1.57
     planes
    1.38
    plane
    1.27
     Plane
    1.26
     plan
    1.23
    planes
    1.21
     planos
    1.18
     PLANE
    1.17
    plan
    1.15
     Plan
    1.14
    Activations Density 2.003%

    No Known Activations