© 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. 11536
    Prev
    Next
    INDEX
    Explanations

    table-like structures with numbers and medical terms, and also bulleted lists of names with affiliations.

    oai_token-act-pair · gemini-2.0-flash

    proper nouns abbreviations

    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
     di
    -1.02
     «
    -0.98
     van
    -0.92
     I
    -0.91
     Di
    -0.90
     J
    -0.90
     der
    -0.89
    CRIPTION
    -0.89
     qu
    -0.89
     Is
    -0.88
    POSITIVE LOGITS
     itſelf
    1.42
     myſelf
    1.27
     Anſ
    1.26
     Majefty
    1.24
     greateſt
    1.22
     Shakspeare
    1.21
     pleaſure
    1.21
     Cæsar
    1.20
     Chriftian
    1.18
     raiſ
    1.17
    Activations Density 2.875%

    No Known Activations