© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5643
    Prev
    Next
    INDEX
    Explanations

    descriptions of people's appearance while committing crimes

    oai_token-act-pair · gemini-2.0-flash

    Clothing/covering

    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
     referenties
    -0.66
     endforeach
    -0.62
     aceptas
    -0.59
     تانيه
    -0.54
    __':
    -0.51
    fjspx
    -0.50
    </>
    -0.49
    ScopeManager
    -0.49
     FishBase
    -0.48
    lau
    -0.47
    POSITIVE LOGITS
     betweenstory
    0.85
    ArrowToggle
    0.84
    IUrlHelper
    0.56
    +#+#
    0.55
    Artik
    0.53
    inaires
    0.52
     domo
    0.48
    AntiForgeryToken
    0.48
    ZM
    0.48
     association
    0.48
    Activations Density 0.764%

    No Known Activations