© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14497
    Prev
    Next
    INDEX
    Explanations

    words related to harm, injury, and destruction

    oai_token-act-pair · gemini-2.0-flash

    Damage, mistakes, and errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     autorytatywna
    -0.66
     Attitudes
    -0.58
    iibo
    -0.57
    Viitteet
    -0.57
     tartalomajánló
    -0.57
    ronique
    -0.55
    AllAfrica
    -0.54
    FTFY
    -0.52
     volte
    -0.50
     Boyer
    -0.50
    POSITIVE LOGITS
     damage
    1.34
     damages
    1.18
     daño
    1.09
     Damage
    1.08
    damage
    1.05
    Damage
    1.05
     danni
    1.03
     Damages
    1.02
     damaged
    1.00
     daños
    0.99
    Activations Density 1.436%

    No Known Activations