© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10296
    Prev
    Next
    INDEX
    Explanations

    angle brackets used in code

    oai_token-act-pair · gemini-2.0-flash

    archaic or stylized spellings of "self"

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

    Code snippets

    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
    NameInMap
    -0.66
     Man
    -0.64
     s
    -0.62
     ($
    -0.62
     K
    -0.61
     co
    -0.58
     us
    -0.58
     in
    -0.57
     si
    -0.57
     b
    -0.56
    POSITIVE LOGITS
     itſelf
    0.92
     Majefty
    0.81
     houſe
    0.77
     Jefus
    0.76
     myſelf
    0.76
    ſelf
    0.75
     pleaſure
    0.75
     doubtnut
    0.73
     ་་
    0.73
     PLW
    0.71
    Activations Density 7.936%

    No Known Activations