© 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. 15765
    Prev
    Next
    INDEX
    Explanations

    mentions of the history of a church and its restoration

    oai_token-act-pair · gemini-2.0-flash

    historical buildings

    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
     protoimpl
    -0.54
     springfox
    -0.51
    archiviato
    -0.51
    FieldDescriptor
    -0.49
     PyObject
    -0.47
    zuma
    -0.47
     Heil
    -0.46
    BASEPATH
    -0.46
     pa
    -0.46
    xffffffff
    -0.46
    POSITIVE LOGITS
    #+#
    0.74
     Efq
    0.63
     habet
    0.63
    Chevrolet
    0.59
     eût
    0.58
     échou
    0.57
     chofe
    0.57
     aveug
    0.57
    ėk
    0.57
     chêne
    0.54
    Activations Density 8.436%

    No Known Activations