© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9763
    Prev
    Next
    INDEX
    Explanations

    sentiment and emotional expression in the text.

    oai_token-act-pair · gemini-2.0-flash

    of/to

    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
     CreateTagHelper
    -0.98
    ंदीखरीदारी
    -0.97
     للاسماء
    -0.96
    $.
    -0.81
     سكانية
    -0.80
     HttpNotFound
    -0.77
    évaluateur
    -0.77
    IVEREF
    -0.76
     فريبيس
    -0.76
    ulipas
    -0.75
    POSITIVE LOGITS
     it
    0.90
     the
    0.82
     any
    0.68
     this
    0.68
     what
    0.63
     how
    0.57
     your
    0.56
     these
    0.56
     me
    0.54
     us
    0.52
    Activations Density 7.770%

    No Known Activations