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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15384
    Prev
    Next
    INDEX
    Explanations

    sentences using auxiliary verbs such as "can", "will", "do", "have", "be", and sometimes "must", "get" and "should"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ftagPool
    -0.67
    DebuggerNonUser
    -0.66
    ViewFeatures
    -0.62
    ValueStyle
    -0.58
    setViewportView
    -0.57
    ⓧ
    -0.56
    TagMode
    -0.56
    DeleteBehavior
    -0.55
    DataAnnotations
    -0.54
    migrationBuilder
    -0.52
    POSITIVE LOGITS
    REFERRED
    0.54
    rouse
    0.53
     wies
    0.51
     Americana
    0.50
    ziest
    0.50
    newArrayList
    0.49
    Système
    0.48
     порядке
    0.48
     Schenk
    0.47
    ificance
    0.47
    Activations Density 5.943%

    No Known Activations