© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9858
    Prev
    Next
    INDEX
    Explanations

    sentences and clauses that express the state of being

    oai_token-act-pair · gemini-2.0-flash

    programming-related keywords

    np_token-act-pair-logits · gpt-4o-mini

    sports articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     disponibilités
    -0.55
    youts
    -0.55
    iomanip
    -0.54
    osoever
    -0.53
    IMPORTED
    -0.52
    Schriften
    -0.51
    pozdrawiam
    -0.50
    ثيق
    -0.50
    wiście
    -0.49
     Wikiseite
    -0.49
    POSITIVE LOGITS
    EndGlobalSection
    0.63
    Tikang
    0.63
     experiencing
    0.62
    NameInMap
    0.61
    resave
    0.60
     CreateTagHelper
    0.59
     nahilalakip
    0.57
     capable
    0.55
    :✨
    0.55
     experienced
    0.54
    Activations Density 0.648%

    No Known Activations