© 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. 9309
    Prev
    Next
    INDEX
    Explanations

    sentences with multiple potentially important words

    oai_token-act-pair · gemini-2.0-flash

    danger or harm

    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
     mild
    -0.63
     douce
    -0.63
     milder
    -0.63
     mellow
    -0.63
     softer
    -0.61
     gentle
    -0.60
     docile
    -0.58
     softly
    -0.57
     Calm
    -0.57
     Mild
    -0.57
    POSITIVE LOGITS
     sharp
    0.84
    sharp
    0.77
    
    0.76
     aggressive
    0.71
     harsh
    0.69
     dangerous
    0.67
     Harsh
    0.67
     sharper
    0.66
     abrupt
    0.65
     hazardous
    0.64
    Activations Density 2.290%

    No Known Activations