© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13615
    Prev
    Next
    INDEX
    Explanations

    code snippets, math equations, or any kind of unreadable formulas or notations

    oai_token-act-pair · gemini-2.0-flash

    code/math/computer language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    twimg
    -0.85
    InjectAttribute
    -0.68
    Portale
    -0.68
    HostException
    -0.66
     Савезне
    -0.64
    脚注の使い方
    -0.63
     Jefus
    -0.63
    NUMX
    -0.61
    {}{}
    -0.60
     doubtnut
    -0.59
    POSITIVE LOGITS
    stuhl
    0.55
     sûr
    0.48
    mad
    0.45
    cocc
    0.43
     onOptions
    0.43
     directement
    0.42
     Mad
    0.42
    快
    0.42
    ist
    0.42
     parte
    0.41
    Activations Density 2.538%

    No Known Activations