© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13274
    Prev
    Next
    INDEX
    Explanations

    the punctuation at the end of sentences along with license or copyright related words

    oai_token-act-pair · gemini-2.0-flash

    Technical/legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     They
    -1.28
     There
    -1.12
     It
    -1.09
     Its
    -1.05
     Their
    -1.02
    They
    -1.00
     You
    -0.98
     Those
    -0.97
     The
    -0.97
     This
    -0.94
    POSITIVE LOGITS
    出版年
    0.78
    OGND
    0.75
     esternos
    0.71
    tvguidetime
    0.68
    __":
    0.68
    DockStyle
    0.67
     Audiodateien
    0.65
     unknownFields
    0.64
     we
    0.64
    DispatchToProps
    0.62
    Activations Density 3.213%

    No Known Activations