© 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. 1048
    Prev
    Next
    INDEX
    Explanations

    segments of text about electronic circuits, especially amplifiers

    oai_token-act-pair · gemini-2.0-flash

    rare words

    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
    -0.73
    /***/
    -0.69
     تانيه
    -0.65
    expandindo
    -0.64
    COUVER
    -0.61
    
    -0.57
    findpost
    -0.57
     jspb
    -0.52
    unhofer
    -0.52
    complexType
    -0.52
    POSITIVE LOGITS
    DataBind
    0.49
     Eichen
    0.48
    ειτουργ
    0.46
     Bernoulli
    0.45
     motion
    0.44
     Préférences
    0.43
    tgärder
    0.43
    吞
    0.42
    dorfer
    0.41
    FontFamily
    0.41
    Activations Density 2.288%

    No Known Activations