© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3985
    Prev
    Next
    INDEX
    Explanations

    words related to describing or classifying information

    oai_token-act-pair · gemini-2.0-flash

    characterized

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     characterized
    -0.65
    labelledby
    -0.63
    multer
    -0.59
     “
    -0.59
    rack
    -0.59
    oms
    -0.59
    du
    -0.56
     Ceci
    -0.56
    Ultimately
    -0.56
    ers
    -0.56
    POSITIVE LOGITS
    تقاوى
    0.98
    oredCriteria
    0.90
     beginnetje
    0.84
    uxxxx
    0.84
    IUrlHelper
    0.83
    الحياه
    0.81
    <bos>
    0.80
     licences
    0.80
    UnknownFields
    0.79
     resourceCulture
    0.77
    Activations Density 1.260%

    No Known Activations