© 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. 10305
    Prev
    Next
    INDEX
    Explanations

    verbs

    oai_token-act-pair · 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
     виправивши
    -0.51
     leksikon
    -0.42
     them
    -0.41
    unteer
    -0.41
     grises
    -0.41
    Reel
    -0.40
     straw
    -0.40
    IBarButtonItem
    -0.40
    QRST
    -0.40
     нас
    -0.38
    POSITIVE LOGITS
    WebVitals
    0.72
    MigrationBuilder
    0.63
     youll
    0.62
    Gambas
    0.62
    Enllaces
    0.62
    ът
    0.61
    postsleuth
    0.61
    NameInMap
    0.60
    aliers
    0.60
     onCreateView
    0.60
    Activations Density 1.677%

    No Known Activations