© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12740
    Prev
    Next
    INDEX
    Explanations

    names and titles of people and sometimes family names

    oai_token-act-pair · gemini-2.0-flash

    ers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     aveug
    -0.40
     agré
    -0.40
     Lietu
    -0.40
    クリート
    -0.40
     giac
    -0.39
     květ
    -0.39
    扒
    -0.38
     terakhir
    -0.37
    Complex
    -0.37
     peluang
    -0.37
    POSITIVE LOGITS
     nahilalakip
    1.18
    脚注の使い方
    1.13
    +#+#
    1.09
    Personensuche
    1.05
     المعيارى
    1.04
     utafitiHapana
    1.03
     snippetHide
    1.00
     CURIAM
    0.95
    localctx
    0.93
     initComponents
    0.93
    Activations Density 0.649%

    No Known Activations