© 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. 15508
    Prev
    Next
    INDEX
    Explanations

    capitalized words or phrases, and words relating to medical, legal, scientific or architectural fields

    oai_token-act-pair · gemini-2.0-flash

    scientific

    np_max-act · gemini-2.0-flash

    say "attachment" Method used: 2 — tokens after show attachment/linking words

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    a
    -0.73
    ます
    -0.61
     
    -0.57
    A
    -0.57
    ":
    -0.57
    the
    -0.55
    ACES
    -0.55
     $
    -0.55
    𝐝
    -0.54
    e
    -0.53
    POSITIVE LOGITS
    <bos>
    1.53
    WebVitals
    1.30
     Paglinawan
    1.25
     autorytatywna
    1.16
     ProtoMessage
    1.14
     GenerationType
    1.10
    PreferredItem
    1.09
    UnusedPrivate
    1.06
     AssemblyCompany
    1.05
     تضيفلها
    1.05
    Activations Density 22.225%

    No Known Activations