© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6257
    Prev
    Next
    INDEX
    Explanations

    hexadecimal and IP addresses

    oai_token-act-pair · gemini-2.0-flash

    number "four"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     bezeichneter
    -0.69
     Bourgoin
    -0.67
    ########.
    -0.66
    Rhestr
    -0.60
     виправивши
    -0.59
     سكانية
    -0.53
    Rüyada
    -0.52
     tartalomajánló
    -0.52
     disambiguazione
    -0.51
     JpaRepository
    -0.51
    POSITIVE LOGITS
     four
    1.33
    4
    1.23
     Four
    1.04
     vier
    0.99
    four
    0.98
     четыре
    0.96
     cuatro
    0.96
     четырех
    0.94
     quatro
    0.93
     FOUR
    0.91
    Activations Density 1.234%

    No Known Activations