© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13928
    Prev
    Next
    INDEX
    Explanations

    code snippets or code-related vocabulary

    oai_token-act-pair · gemini-2.0-flash

    Non-English 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_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
     betweenstory
    -0.68
    usermodel
    -0.61
    EndInit
    -0.59
    GEBURTSDATUM
    -0.56
     disambiguazione
    -0.56
     Feinde
    -0.56
    InputBorder
    -0.56
    InitVars
    -0.54
    örk
    -0.54
     références
    -0.54
    POSITIVE LOGITS
     cubrir
    0.88
     grabar
    0.87
     presentar
    0.84
     dominar
    0.84
     competir
    0.83
     fabricar
    0.83
     disminuir
    0.83
     operar
    0.82
     eseguire
    0.82
     guardare
    0.82
    Activations Density 0.748%

    No Known Activations