© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10083
    Prev
    Next
    INDEX
    Explanations

    code snippets with numbers and multiplication

    oai_token-act-pair · gemini-2.0-flash

    zero

    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
    RectangleBorder
    -1.01
     initComponents
    -0.99
     BoxFit
    -0.94
    CloseOperation
    -0.91
    SupportActionBar
    -0.88
    httphttps
    -0.88
     Мексичка
    -0.85
    tagHelperRunner
    -0.84
    4
    -0.81
     beginnetje
    -0.81
    POSITIVE LOGITS
    0
    0.56
    ０
    0.40
    ه
    0.39
     ۰
    0.36
    E
    0.34
     und
    0.33
    ene
    0.33
    min
    0.32
     m
    0.32
     min
    0.31
    Activations Density 7.320%

    No Known Activations