© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 4061
    Prev
    Next
    INDEX
    Explanations

    words about making space, whether in a computer or one's mind

    oai_token-act-pair · gemini-2.0-flash

    concept of "space"

    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
     Wikimedijinoj
    -0.85
     Spaces
    -0.84
    Spaces
    -0.83
     الحره
    -0.82
    yntaxException
    -0.82
     cherchés
    -0.81
     kaynağından
    -0.79
    jsxFileName
    -0.78
    spaces
    -0.77
     spaces
    -0.76
    POSITIVE LOGITS
     pace
    0.55
     spa
    0.53
     SP
    0.53
     không
    0.49
     sp
    0.47
     Spa
    0.47
     pl
    0.47
    SP
    0.44
    sp
    0.42
     sap
    0.41
    Activations Density 1.631%

    No Known Activations