© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9253
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings, defendants, and statements related to the case

    oai_token-act-pair · gemini-2.0-flash

    defendant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    <bos>
    -1.56
     võimal
    -0.50
    كويكب
    -0.45
     BoxDecoration
    -0.43
    yntaxException
    -0.43
    ьаж
    -0.41
    abord
    -0.40
     recente
    -0.40
     trava
    -0.40
     répé
    -0.40
    POSITIVE LOGITS
    principalTable
    0.76
    serviceWorker
    0.71
    VersionUID
    0.65
    wikidata
    0.65
    didSet
    0.64
     tkinter
    0.62
    èdia
    0.61
     متعلقه
    0.59
    ViewInit
    0.59
    InteropServices
    0.58
    Activations Density 9.959%

    No Known Activations