© 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. 6723
    Prev
    Next
    INDEX
    Explanations

    geographic place names or locations, sometimes with surrounding context words

    oai_token-act-pair · gemini-2.0-flash

    proper nouns and locations

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

    Carolina area

    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
     My
    -0.42
     rendel
    -0.40
    M
    -0.40
     vorder
    -0.39
    hilangan
    -0.39
    My
    -0.39
     M
    -0.37
     Col
    -0.35
     menny
    -0.34
     thing
    -0.33
    POSITIVE LOGITS
     CreateTagHelper
    0.99
     EconPapers
    0.90
    TestTools
    0.90
    LayoutConstraint
    0.83
    GraphicsUnit
    0.82
    principalColumn
    0.79
     <<<<<<<<<<<<<<
    0.78
     protoimpl
    0.76
     незавершена
    0.76
    ChildScrollView
    0.75
    Activations Density 1.086%

    No Known Activations