© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11194
    Prev
    Next
    INDEX
    Explanations

    phrases which express a mitigating or negating opinion

    oai_token-act-pair · gemini-2.0-flash

    bad

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     nice
    -0.75
     تضيفلها
    -0.74
     Nice
    -0.72
     ArrayAdapter
    -0.68
    nice
    -0.66
    Nice
    -0.66
     pleasant
    -0.65
    ValueGeneration
    -0.65
    GraphicsUnit
    -0.63
     good
    -0.60
    POSITIVE LOGITS
     bad
    1.47
    bad
    1.30
    Bad
    1.22
     Bad
    1.13
    BAD
    1.06
     BAD
    1.05
     schlecht
    0.84
     mauvaise
    0.84
     wrong
    0.82
     rossz
    0.77
    Activations Density 0.502%

    No Known Activations