© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2761
    Prev
    Next
    INDEX
    Explanations

    phrases with "all" followed by a hyphen.

    oai_token-act-pair · gemini-2.0-flash

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     AssemblyTitle
    -0.65
     over
    -0.54
    вок
    -0.50
    انظر
    -0.49
    Over
    -0.49
    ease
    -0.48
    iencias
    -0.48
    All
    -0.47
    PageContext
    -0.47
     fuis
    -0.46
    POSITIVE LOGITS
    AndEndTag
    0.71
     للاسماء
    0.67
     surla
    0.66
     يتيمه
    0.59
    SharedCtor
    0.57
    BorderFactory
    0.57
    fjspx
    0.56
     للمعارف
    0.53
    gypti
    0.52
    gemeester
    0.51
    Activations Density 1.002%

    No Known Activations