© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 8560
    Prev
    Next
    INDEX
    Explanations

    text related to political issues like repatriation or citizenship, as well as song titles and references to women

    oai_token-act-pair · gemini-2.0-flash

    Snippets of 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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Spreadsheet
    -0.84
     Updated
    -0.83
     Download
    -0.81
     Reprint
    -0.81
     Screenshot
    -0.78
     Transcript
    -0.78
     Printable
    -0.77
     Revised
    -0.75
     Template
    -0.75
     Sample
    -0.75
    POSITIVE LOGITS
     Life
    0.66
     Mind
    0.59
    Kind
    0.58
    Life
    0.57
     Love
    0.57
     Humanity
    0.56
     Family
    0.56
     Kind
    0.53
    Family
    0.53
     Force
    0.52
    Activations Density 7.912%

    No Known Activations