© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12634
    Prev
    Next
    INDEX
    Explanations

    code, numbers, and quotation marks

    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
     د
    -0.43
     و
    -0.42
     ل
    -0.41
     س
    -0.41
     م
    -0.39
     ا
    -0.38
     ست
    -0.38
     وال
    -0.37
     ب
    -0.36
     من
    -0.36
    POSITIVE LOGITS
     Efq
    0.66
     raiſ
    0.64
     purpoſe
    0.59
     itſelf
    0.58
     Conſ
    0.57
     pleaſure
    0.56
     cauſe
    0.56
     diſt
    0.55
     poffe
    0.55
     ſp
    0.54
    Activations Density 3.589%

    No Known Activations