© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6926
    Prev
    Next
    INDEX
    Explanations

    verbs, especially ones ending in -ize, -ise, -ate, -ed, -ing, or -s

    oai_token-act-pair · gemini-2.0-flash

    Suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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>
    -1.95
     the
    -0.59
    '
    -0.54
    S
    -0.52
    So
    -0.52
    ’
    -0.50
    В
    -0.49
    To
    -0.47
    For
    -0.46
    -
    -0.45
    POSITIVE LOGITS
     DialogInterface
    0.90
     AssemblyCulture
    0.78
     NSCoder
    0.77
    +#+#
    0.75
    InputBorder
    0.72
    ReusableCell
    0.72
    UIControlState
    0.70
     InputDecoration
    0.68
     Preferencias
    0.68
     محفوظة
    0.66
    Activations Density 5.482%

    No Known Activations