© 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. 12657
    Prev
    Next
    INDEX
    Explanations

    words indicating feelings and thoughts

    oai_token-act-pair · gemini-2.0-flash

    Perspective and discovery

    np_max-act · gemini-2.0-flash

    trust and suspicion

    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_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
     utafitiHapana
    -0.79
    queryInterface
    -0.77
    createCanvas
    -0.77
    expandindo
    -0.76
     autorytatywna
    -0.75
     חיצוניים
    -0.75
    ---*/
    -0.74
     initComponents
    -0.71
     Normdatei
    -0.71
     CURIAM
    -0.70
    POSITIVE LOGITS
    entra
    0.47
     box
    0.45
    enovo
    0.44
     let
    0.43
     tro
    0.43
     self
    0.43
     heavy
    0.42
    n
    0.42
    iol
    0.41
     CURLOPT
    0.41
    Activations Density 2.239%

    No Known Activations