© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3242
    Prev
    Next
    INDEX
    Explanations

    descriptions of a person and their features, particularly eyes

    oai_token-act-pair · gemini-2.0-flash

    characteristics of a person

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    മ്
    -0.45
     poro
    -0.45
     Lectures
    -0.44
     lectures
    -0.42
    /*"
    -0.42
     Lees
    -0.41
    >);
    -0.41
     Bayard
    -0.41
     svm
    -0.41
    stalt
    -0.40
    POSITIVE LOGITS
    fjspx
    0.92
     protoimpl
    0.81
    setVerticalGroup
    0.77
     gynhyrchwyd
    0.77
    NameInMap
    0.72
     GenerationType
    0.69
    AndEndTag
    0.69
    extAlignment
    0.68
    expandindo
    0.66
     Réponses
    0.66
    Activations Density 1.220%

    No Known Activations