© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14124
    Prev
    Next
    INDEX
    Explanations

    references to emotions and the experience of feeling

    oai_token-act-pair · gemini-2.0-flash

    expressions of feelings

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

    feel

    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
    InitStruct
    -0.56
    脚注の使い方
    -0.56
    LookAnd
    -0.54
    ServletException
    -0.54
    jsonwebtoken
    -0.54
    adomo
    -0.50
    Spacer
    -0.47
     Ancona
    -0.47
    openqa
    -0.47
     CommonModule
    -0.47
    POSITIVE LOGITS
     feel
    0.79
     Feel
    0.79
    Feel
    0.75
     feels
    0.71
     self
    0.67
     feeling
    0.66
    feel
    0.65
    bootstrapcdn
    0.63
     guilt
    0.63
     FEEL
    0.62
    Activations Density 1.685%

    No Known Activations