© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9904
    Prev
    Next
    INDEX
    Explanations

    the word "layer"

    oai_token-act-pair · gemini-2.0-flash

    layer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     تضيفلها
    -1.21
     pinulongan
    -1.20
     onPostExecute
    -1.17
     nakalista
    -1.16
     ainfi
    -1.10
     Efq
    -1.10
    tagHelperRunner
    -1.09
    تقاوى
    -1.04
     صوتيه
    -1.01
    GEBURTSDATUM
    -1.01
    POSITIVE LOGITS
     
    1.13
     “
    0.90
     and
    0.73
     T
    0.73
     "
    0.72
     in
    0.69
     S
    0.67
    ’
    0.66
     a
    0.65
     or
    0.65
    Activations Density 1.444%

    No Known Activations