© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6204
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names of people

    oai_token-act-pair · gemini-2.0-flash

    Names or companies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     partie
    -0.46
    gio
    -0.39
     szer
    -0.38
     Anda
    -0.38
     imobili
    -0.38
    rę
    -0.38
     menti
    -0.38
    ach
    -0.38
    Deja
    -0.38
     della
    -0.37
    POSITIVE LOGITS
    AndEndTag
    1.20
    DockStyle
    1.11
    ConstraintMaker
    1.10
    Personensuche
    1.06
     propOrder
    1.02
     snippetHide
    1.02
     StringTokenizer
    1.01
     سكانية
    1.00
     Réponses
    1.00
    InputBorder
    1.00
    Activations Density 1.991%

    No Known Activations