© 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. 12249
    Prev
    Next
    INDEX
    Explanations

    words that commonly have the letters 'f', 'r', or 'v' as the second letter

    oai_token-act-pair · gemini-2.0-flash

    vem

    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
     EconPapers
    -0.59
     Alamy
    -0.56
     vectorielles
    -0.56
    AMAHA
    -0.56
     étrangères
    -0.56
     lautet
    -0.55
    ودی
    -0.55
    SPATH
    -0.54
     suivants
    -0.53
     MIP
    -0.53
    POSITIVE LOGITS
    VIAF
    0.66
    <bos>
    0.62
    MethodManager
    0.59
     typelib
    0.57
     over
    0.56
    over
    0.55
     numberOfRows
    0.54
    Over
    0.54
     OVER
    0.53
     Over
    0.51
    Activations Density 0.242%

    No Known Activations