© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13573
    Prev
    Next
    INDEX
    Explanations

    mostly German language words

    oai_token-act-pair · gemini-2.0-flash

    Non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     تضيفلها
    -1.06
     myſelf
    -0.89
     Anſ
    -0.87
     Monfieur
    -0.81
     Cæsar
    -0.81
     Majefty
    -0.80
    Rhestr
    -0.79
     itſelf
    -0.79
     Reſ
    -0.75
     himſelf
    -0.75
    POSITIVE LOGITS
    ss
    0.55
    smo
    0.51
    SM
    0.51
    sd
    0.49
    sm
    0.48
    aville
    0.48
    sve
    0.46
    ssn
    0.45
    sf
    0.45
    spli
    0.44
    Activations Density 0.924%

    No Known Activations