© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3930
    Prev
    Next
    INDEX
    Explanations

    instances of subjective feelings

    oai_token-act-pair · gemini-2.0-flash

    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_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
     case
    -0.50
     yo
    -0.42
    f
    -0.42
     []:
    -0.42
    R
    -0.40
    F
    -0.39
     cas
    -0.39
    Me
    -0.39
    D
    -0.39
    volving
    -0.38
    POSITIVE LOGITS
    IntoConstraints
    0.91
     SafeMath
    0.85
    yntaxException
    0.79
    >{@
    0.77
    ✨:
    0.77
    ^(@)
    0.75
     Paglinawan
    0.74
    hermosa
    0.73
    ,:);
    0.72
    tanleria
    0.72
    Activations Density 4.578%

    No Known Activations