© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13181
    Prev
    Next
    INDEX
    Explanations

    negative language and profanity

    oai_token-act-pair · gemini-2.0-flash

    offensive language

    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
     purpoſe
    -0.93
     itſelf
    -0.91
     myſelf
    -0.89
     raiſ
    -0.87
     Reſ
    -0.86
     ſte
    -0.85
     ſtate
    -0.84
     ſta
    -0.84
     poffible
    -0.83
    ſelf
    -0.82
    POSITIVE LOGITS
     di
    0.58
     sus
    0.47
     f
    0.47
     createSlice
    0.47
     per
    0.47
    FilterChain
    0.45
     eff
    0.45
     su
    0.44
     w
    0.44
     pus
    0.44
    Activations Density 0.898%

    No Known Activations