© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14638
    Prev
    Next
    INDEX
    Explanations

    dates of historic events

    oai_token-act-pair · gemini-2.0-flash

    the

    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
    GO
    -0.46
     Des
    -0.45
    paž
    -0.43
    Des
    -0.43
    ever
    -0.42
     Sosten
    -0.39
    addPreferredGap
    -0.37
     sosis
    -0.37
    Nog
    -0.37
    no
    -0.37
    POSITIVE LOGITS
     myſelf
    0.77
     Reſ
    0.73
    Sucesor
    0.68
     expulsion
    0.68
     itſelf
    0.66
     themſelves
    0.65
    ModelAdmin
    0.65
    ſelves
    0.65
    ientôt
    0.65
     himſelf
    0.65
    Activations Density 1.625%

    No Known Activations