© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5737
    Prev
    Next
    INDEX
    Explanations

    instances where someone is expressing feelings or emotion

    oai_token-act-pair · gemini-2.0-flash

    feel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     myſelf
    -1.20
     pleaſure
    -1.16
     Efq
    -1.12
    DockStyle
    -1.10
     Jefus
    -1.09
     Majefty
    -1.08
    verwijspagina
    -1.05
     Monfieur
    -1.03
     Anſ
    -1.01
     themſelves
    -1.00
    POSITIVE LOGITS
     so
    0.73
     to
    0.70
     an
    0.66
     a
    0.66
     
    0.63
    nbsp
    0.60
     am
    0.59
     is
    0.59
     er
    0.58
     be
    0.58
    Activations Density 0.242%

    No Known Activations