© 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. 11721
    Prev
    Next
    INDEX
    Explanations

    mentions of file systems, particularly Xsan

    oai_token-act-pair · gemini-2.0-flash

    Computer files and systems

    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
     rospy
    -0.75
    AndEndTag
    -0.73
    PreferredItem
    -0.69
    Jeografia
    -0.68
    bootstrapcdn
    -0.68
     незавершена
    -0.68
     كومونز
    -0.68
    NameInMap
    -0.68
    PYX
    -0.67
    MessageTagHelper
    -0.67
    POSITIVE LOGITS
    unbind
    0.48
    ACKS
    0.46
    اش
    0.46
     Spiegel
    0.46
    AUDIT
    0.45
     isolation
    0.45
     disarm
    0.45
    Auditor
    0.45
     Bind
    0.43
    EMAS
    0.43
    Activations Density 4.595%

    No Known Activations