© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6114
    Prev
    Next
    INDEX
    Explanations

    words related to plants, cells, genetics, and scientific experiments

    oai_token-act-pair · gemini-2.0-flash

    cell biology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Personensuche
    -0.67
    InjectMocks
    -0.66
     betweenstory
    -0.65
    +#+#
    -0.64
    complexContent
    -0.63
    endphp
    -0.62
    èvres
    -0.56
     SqlCommand
    -0.56
     protoimpl
    -0.52
     IBOutlet
    -0.51
    POSITIVE LOGITS
     differentiation
    0.62
    soma
    0.56
     dividing
    0.56
     Differentiation
    0.56
     organ
    0.55
     regener
    0.55
     divide
    0.55
     division
    0.54
     Regeneration
    0.53
    الدراسه
    0.53
    Activations Density 4.662%

    No Known Activations