© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15674
    Prev
    Next
    INDEX
    Explanations

    numbers, especially years

    oai_token-act-pair · gemini-2.0-flash

    Legal, code, and citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     S
    -0.45
     odkazy
    -0.44
     W
    -0.44
    s
    -0.43
    nt
    -0.43
    <bos>
    -0.42
    alo
    -0.42
     ý
    -0.42
     R
    -0.42
    imgur
    -0.41
    POSITIVE LOGITS
    RenderAtEndOf
    0.94
    BufferException
    0.82
    ValueStyle
    0.80
    FunctionFlags
    0.77
    CloseOperation
    0.77
    \{\\
    0.74
     فريبيس
    0.71
     transfieras
    0.71
    VersionUID
    0.70
    SequentialGroup
    0.67
    Activations Density 0.615%

    No Known Activations