© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10743
    Prev
    Next
    INDEX
    Explanations

    words or phrases about health, economics, and children

    oai_token-act-pair · gemini-2.0-flash

    insecurity

    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
    CrossRef
    -0.48
    ütfen
    -0.45
    CloseOperation
    -0.44
     menar
    -0.43
     most
    -0.43
     ISNI
    -0.43
    riek
    -0.43
     WaitForSeconds
    -0.42
     métiers
    -0.42
    Gweler
    -0.41
    POSITIVE LOGITS
     Phry
    0.71
     reft
    0.69
     Efq
    0.68
     PPD
    0.68
     XE
    0.66
     ་་
    0.65
     raiſ
    0.63
    EndContext
    0.63
     itſelf
    0.63
     HSA
    0.63
    Activations Density 5.974%

    No Known Activations