© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9543
    Prev
    Next
    INDEX
    Explanations

    document structures such as titles, editions, and numbered items

    oai_token-act-pair · gemini-2.0-flash

    Italy, Italian, text modifications

    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
     AssemblyCulture
    -0.89
    IsMutable
    -0.83
    VersionUID
    -0.77
     незавершена
    -0.70
    extAlignment
    -0.67
    phosa
    -0.66
     kasarigan
    -0.66
    OptionsMenu
    -0.62
    ContentAsync
    -0.60
    InitVars
    -0.60
    POSITIVE LOGITS
     come
    0.57
    ModelMap
    0.54
     partial
    0.53
    come
    0.51
    uttgart
    0.50
    ifikant
    0.50
    杵
    0.48
     Come
    0.47
     COME
    0.47
     useRef
    0.46
    Activations Density 0.448%

    No Known Activations