© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12092
    Prev
    Next
    INDEX
    Explanations

    single upper-case letters

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    出版年
    -0.54
     defStyleAttr
    -0.53
    cero
    -0.51
     témoins
    -0.51
     Barclay
    -0.51
     Intens
    -0.50
    JoinColumn
    -0.49
    IconModule
    -0.49
    라이
    -0.49
    rows
    -0.48
    POSITIVE LOGITS
    NUMX
    0.66
    DebuggerStep
    0.62
    SDAY
    0.62
     }}$}
    0.58
    VERTISEMENT
    0.57
    PhysRev
    0.56
    UseVisualStyle
    0.53
    UNICIP
    0.53
    SequentialGroup
    0.52
    nastics
    0.52
    Activations Density 0.401%

    No Known Activations