© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5953
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "take for granted," and other language related to elections and politics

    oai_token-act-pair · gemini-2.0-flash

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     separating
    -1.21
     dividing
    -1.18
     divider
    -1.17
     separation
    -1.11
     boundary
    -1.07
     separates
    -1.03
     Divider
    -1.02
     divide
    -1.01
     separa
    -0.98
     separator
    -0.97
    POSITIVE LOGITS
     intptr
    0.72
    GraphicsUnit
    0.69
    take
    0.68
    исленность
    0.68
    taken
    0.68
    Билгалдахарш
    0.66
    SourceChecksum
    0.66
     GenerationType
    0.66
    taking
    0.65
    Take
    0.65
    Activations Density 0.485%

    No Known Activations