© 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. 9825
    Prev
    Next
    INDEX
    Explanations

    sentences about recruiting or pointing out people the writer likes and common words

    oai_token-act-pair · gemini-2.0-flash

    People and their attributes

    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
     INTERESAR
    -0.71
    /*
    -0.66
    libft
    -0.65
     typelib
    -0.65
    IntoConstraints
    -0.65
     beginnetje
    -0.64
     eventdata
    -0.63
    rrggbb
    -0.59
     onAnimation
    -0.59
    CopyWith
    -0.58
    POSITIVE LOGITS
    لیس
    0.49
     demonstrate
    0.49
     displays
    0.48
     Microbiology
    0.48
    BoxShadow
    0.47
     believe
    0.46
     Microbiol
    0.46
     portray
    0.45
    пита
    0.44
    ATTRIBUTES
    0.44
    Activations Density 1.965%

    No Known Activations