© 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. 15356
    Prev
    Next
    INDEX
    Explanations

    snippets of code with a few associated words that vary across languages

    oai_token-act-pair · gemini-2.0-flash

    Chat logs

    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
     cubrir
    -0.88
     grabar
    -0.84
     presentar
    -0.83
     dominar
    -0.82
     disminuir
    -0.81
     apresentar
    -0.80
     publicar
    -0.79
     introducir
    -0.79
     acudir
    -0.79
     celebrar
    -0.79
    POSITIVE LOGITS
     betweenstory
    0.58
    GEBURTSDATUM
    0.57
     purpoſe
    0.56
    usermodel
    0.54
    örk
    0.53
    EndInit
    0.53
     disambiguazione
    0.53
    AndEndTag
    0.52
    łucha
    0.52
    InitVars
    0.50
    Activations Density 0.688%

    No Known Activations