© 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. 2419
    Prev
    Next
    INDEX
    Explanations

    the word "zaktype" and funding-related words within a specific context, possibly related to research grants

    oai_token-act-pair · gemini-2.0-flash

    Website text

    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
     autorytatywna
    -0.74
     disambiguazione
    -0.73
    httphttps
    -0.69
    SequentialGroup
    -0.68
     Reverso
    -0.65
    
    -0.65
     AssemblyCulture
    -0.63
    IsContent
    -0.63
    SourceChecksum
    -0.60
    بوابة
    -0.59
    POSITIVE LOGITS
     betweenstory
    0.71
    umbres
    0.53
    rump
    0.45
    ometra
    0.45
    ContentAlignment
    0.44
    gorit
    0.44
    Geografie
    0.44
    Carriera
    0.44
    DllImport
    0.43
    COPYRIGHT
    0.43
    Activations Density 0.138%

    No Known Activations