© 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. 2345
    Prev
    Next
    INDEX
    Explanations

    names of Polish villages and regions, often including "Gmina", "Kłodzko", "Wielkopolska" or "Dolne"

    oai_token-act-pair · gemini-2.0-flash

    Figures in studies

    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
    #+#
    -0.79
     ExecuteAsync
    -0.69
    RegressionTest
    -0.68
    featureID
    -0.63
     Tind
    -0.62
    BeginInit
    -0.60
    EndContext
    -0.59
    Eloquent
    -0.59
     ujednoznacz
    -0.59
     EconPapers
    -0.57
    POSITIVE LOGITS
    uxxxx
    0.46
    Geplaatst
    0.46
    leby
    0.45
     exemplaires
    0.45
     ModelAndView
    0.44
    sidemargin
    0.44
    ecco
    0.42
    Markup
    0.42
    υμα
    0.41
    i
    0.41
    Activations Density 0.165%

    No Known Activations