© 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. 14587
    Prev
    Next
    INDEX
    Explanations

    words related to personal opinions and experiences, especially when contrasted with other viewpoints

    oai_token-act-pair · gemini-2.0-flash

    emotional responses to situations

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

    feelings

    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
    reht
    -0.49
     riviera
    -0.48
    tonode
    -0.46
     cantilever
    -0.46
     ternary
    -0.46
     vif
    -0.45
    BASEPATH
    -0.45
     inverse
    -0.45
     Inverse
    -0.43
     Dickey
    -0.43
    POSITIVE LOGITS
     annoyed
    1.16
     bothers
    1.15
     intrigued
    1.13
     scares
    1.13
     fascin
    1.13
     surprised
    1.13
     bothered
    1.11
     impressed
    1.09
     annoys
    1.09
     frighten
    1.08
    Activations Density 2.106%

    No Known Activations