© 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. 15744
    Prev
    Next
    INDEX
    Explanations

    information sources of different types

    oai_token-act-pair · gemini-2.0-flash

    printed materials/containers

    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
    رشف
    -0.66
    leno
    -0.59
    كويكب
    -0.58
    ]>=
    -0.56
     ExecuteAsync
    -0.52
    thebibliography
    -0.52
    ')['
    -0.52
    WindowConstants
    -0.51
    >());
    -0.50
    StatusBadRequest
    -0.49
    POSITIVE LOGITS
    Mga
    0.52
    cyc
    0.52
     aapt
    0.50
     onCreateView
    0.49
     cul
    0.49
    DrawerToggle
    0.48
     Senna
    0.47
    issé
    0.46
     Selig
    0.46
     xlink
    0.46
    Activations Density 4.062%

    No Known Activations