© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9690
    Prev
    Next
    INDEX
    Explanations

    technical or formal language in a variety of domains, including scientific publications, legal proceedings, business reports, and medical contexts, as well as names and locations.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    rrggbb
    -0.75
    Życiorys
    -0.71
     المعيارى
    -0.71
     getItemCount
    -0.66
    AsUp
    -0.65
    EDEFAULT
    -0.65
    PerformLayout
    -0.63
    ]")]
    -0.63
    IConfiguration
    -0.59
     convertView
    -0.57
    POSITIVE LOGITS
     weekend
    0.46
    rasi
    0.46
     Seconde
    0.45
    leurs
    0.45
    essment
    0.45
    URRED
    0.45
    volo
    0.44
     innovate
    0.44
     Iyer
    0.43
    soni
    0.43
    Activations Density 7.083%

    No Known Activations