© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10523
    Prev
    Next
    INDEX
    Explanations

    words related to feelings of regret or remorse, and to a lesser extent words associated with spirituality

    oai_token-act-pair · gemini-2.0-flash

    regret

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    BeginContext
    -0.66
    ">//
    -0.65
    awtextra
    -0.65
     HasFactory
    -0.64
    ########.
    -0.63
    /**
    -0.63
    abestanden
    -0.62
     jadx
    -0.59
    كويكب
    -0.59
    UnusedPrivate
    -0.59
    POSITIVE LOGITS
     hombro
    0.56
    getActiveSheet
    0.55
     Klan
    0.53
     professeurs
    0.52
    ife
    0.52
     dė
    0.49
     απα
    0.49
     tiroirs
    0.47
     sicura
    0.47
     cerró
    0.46
    Activations Density 6.971%

    No Known Activations