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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2144
    Prev
    Next
    INDEX
    Explanations

    terms related to computer programming, driving, beekeeping or management

    oai_token-act-pair · gemini-2.0-flash

    processes and tasks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     dAtA
    -0.67
    ChildScrollView
    -0.67
    новниш
    -0.65
    numerusform
    -0.65
     resourceCulture
    -0.64
     >=",
    -0.63
    )++;
    -0.61
    InstanceState
    -0.61
    yntaxException
    -0.59
    #+#
    -0.56
    POSITIVE LOGITS
    ocardi
    0.48
     opérateur
    0.47
    WriteTagHelper
    0.46
     médicaux
    0.44
    chitis
    0.42
     dokter
    0.42
    ględ
    0.41
    joni
    0.41
     bomberos
    0.41
     Craft
    0.41
    Activations Density 11.830%

    No Known Activations