© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6118
    Prev
    Next
    INDEX
    Explanations

    words that describe actions

    oai_token-act-pair · gemini-2.0-flash

    worked

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     MainAxisSize
    -1.47
     CreateTagHelper
    -1.45
    AndEndTag
    -1.34
     snippetHide
    -1.30
     متعلقه
    -1.30
    extAlignment
    -1.24
    XmlAccessorType
    -1.21
     صوتيه
    -1.21
     Worked
    -1.20
     '\\;'
    -1.20
    POSITIVE LOGITS
     work
    1.09
     use
    1.02
     the
    0.90
     first
    0.89
     for
    0.89
     a
    0.86
     
    0.84
     in
    0.84
     study
    0.83
     to
    0.82
    Activations Density 2.753%

    No Known Activations