© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14468
    Prev
    Next
    INDEX
    Explanations

    a combination of simple pronouns and verbs, some words with emotional content, and words related to legal or judicial procedures or situations

    oai_token-act-pair · gemini-2.0-flash

    online discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     Superan
    -0.56
     Numerade
    -0.50
    ơi
    -0.46
     serre
    -0.45
    imes
    -0.45
     inexperienced
    -0.45
    anza
    -0.44
     ama
    -0.44
    ctos
    -0.44
    AddressBook
    -0.44
    POSITIVE LOGITS
    HtmlAttribute
    0.66
    IntoConstraints
    0.66
     VIAF
    0.65
     ModelExpression
    0.65
    MergeFrom
    0.61
    ValueStyle
    0.61
    AndEndTag
    0.59
     архивлан
    0.59
    TestingModule
    0.57
     تضيفلها
    0.57
    Activations Density 1.869%

    No Known Activations