© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3218
    Prev
    Next
    INDEX
    Explanations

    mentions of commercially available scientific test or lab kits

    oai_token-act-pair · gemini-2.0-flash

    kit

    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
    ^(@)
    -1.77
     photolibrary
    -1.68
     Efq
    -1.66
    AndEndTag
    -1.66
    StoryboardSegue
    -1.62
    Personendaten
    -1.61
     Forumite
    -1.59
     Мексичка
    -1.59
     ―――――
    -1.54
    SequentialGroup
    -1.52
    POSITIVE LOGITS
    <eos>
    0.95
     
    0.91
    _
    0.81
    @
    0.80
    of
    0.80
    a
    0.77
     [
    0.77
     It
    0.76
    O
    0.75
     If
    0.74
    Activations Density 3.088%

    No Known Activations