© 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. 12459
    Prev
    Next
    INDEX
    Explanations

    HTML artifacts, article beginnings, and conversational cues

    oai_token-act-pair · gemini-2.0-flash

    Read More snippets

    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
    ########.
    -0.65
    Dichloropropane
    -0.62
    Personendaten
    -0.59
    esterday
    -0.57
    Xna
    -0.55
    AddTagHelper
    -0.54
    ⓘ
    -0.54
    سانی
    -0.54
    CopyWith
    -0.54
     فريبيس
    -0.52
    POSITIVE LOGITS
    liothèque
    0.54
     ivelany
    0.53
     åren
    0.48
    modb
    0.46
     aéri
    0.44
    Drops
    0.44
    efel
    0.43
     honnête
    0.43
     duquel
    0.43
    arabe
    0.43
    Activations Density 0.294%

    No Known Activations