© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8740
    Prev
    Next
    INDEX
    Explanations

    words expressing negative emotions or social issues

    oai_token-act-pair · gemini-2.0-flash

    commas and "and"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    MENAFN
    -0.57
     proprement
    -0.52
     déput
    -0.51
     efficacement
    -0.50
     CHAPITRE
    -0.49
     virkelig
    -0.48
     محفوظة
    -0.47
     تانيه
    -0.46
    engertian
    -0.46
     nôtre
    -0.46
    POSITIVE LOGITS
     insufficient
    0.75
    titleMargin
    0.72
     inadequate
    0.66
    دانشنامهٔ
    0.66
     neglect
    0.65
     crime
    0.65
     superstition
    0.63
    extAlignment
    0.63
    rawDesc
    0.63
    rrggbb
    0.62
    Activations Density 5.932%

    No Known Activations