© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3918
    Prev
    Next
    INDEX
    Explanations

    a variety of different kinds of numbers, dates, and codes

    oai_token-act-pair · gemini-2.0-flash

    Code and 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
     espirituales
    -0.75
     judiciales
    -0.68
     varandra
    -0.65
     termica
    -0.65
     industriels
    -0.65
     engraçadas
    -0.65
     oídos
    -0.64
     prisonniers
    -0.64
     prêtres
    -0.64
     élevées
    -0.64
    POSITIVE LOGITS
     Mov
    0.65
     Sma
    0.65
     Twig
    0.65
     GIT
    0.65
     link
    0.65
     Civi
    0.64
     SUA
    0.63
     Opti
    0.61
     Invo
    0.60
     AUX
    0.60
    Activations Density 6.876%

    No Known Activations