© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7067
    Prev
    Next
    INDEX
    Explanations

    sentences containing contractions and personal pronouns

    oai_token-act-pair · gemini-2.0-flash

    Negations

    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
     itſelf
    -0.91
    ſelves
    -0.82
     صوتيه
    -0.81
     myſelf
    -0.79
     Eſ
    -0.77
     ſeveral
    -0.76
    ſelf
    -0.75
     ویکی‌پدیای
    -0.74
     also
    -0.73
     سكانية
    -0.73
    POSITIVE LOGITS
     ever
    0.68
     necessarily
    0.60
     any
    0.60
     EVER
    0.59
    saraba
    0.53
    دانشنامهٔ
    0.53
     anywhere
    0.53
     anymore
    0.52
     necessariamente
    0.52
     exactly
    0.49
    Activations Density 2.127%

    No Known Activations