© 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. 13066
    Prev
    Next
    INDEX
    Explanations

    words in different languages

    oai_token-act-pair · gemini-2.0-flash

    Non-English languages

    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
    <bos>
    -2.22
    '
    -0.69
    ’
    -0.62
     the
    -0.55
    The
    -0.54
    So
    -0.51
    (
    -0.50
    [
    -0.49
    “
    -0.48
    at
    -0.47
    POSITIVE LOGITS
    CloseOperation
    0.79
    󠁢
    0.78
    ]='\
    0.78
     DialogInterface
    0.77
     MainAxisSize
    0.75
    ReusableCell
    0.73
     виправивши
    0.72
    spare
    0.71
    __(/*!
    0.71
     BoxFit
    0.70
    Activations Density 0.511%

    No Known Activations