© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7932
    Prev
    Next
    INDEX
    Explanations

    sentences that include the word "a" and, possibly, "was", "am", or "member"

    oai_token-act-pair · gemini-2.0-flash

    describing a person

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     interpolated
    -0.66
    glLoadIdentity
    -0.56
    endront
    -0.55
    toppers
    -0.55
     viſ
    -0.54
     perſon
    -0.53
    хьтан
    -0.53
    
    -0.53
     Eſ
    -0.53
    giau
    -0.52
    POSITIVE LOGITS
    脚注の使い方
    0.54
     member
    0.53
     former
    0.49
     past
    0.47
     long
    0.47
     mer
    0.46
     hard
    0.45
    SharedCtor
    0.45
     co
    0.45
     Mitglied
    0.45
    Activations Density 0.222%

    No Known Activations