© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4196
    Prev
    Next
    INDEX
    Explanations

    taxonomic descriptions of moths

    oai_token-act-pair · gemini-2.0-flash

    Scientific classification of species

    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
     Insect
    -0.79
     insect
    -0.76
     insectes
    -0.74
     insects
    -0.73
     insecticide
    -0.69
     insec
    -0.68
    sects
    -0.65
     flies
    -0.64
     fly
    -0.64
     pest
    -0.63
    POSITIVE LOGITS
    ftagPool
    0.57
    oplasts
    0.54
     endblock
    0.47
    SupportActionBar
    0.46
    Brainz
    0.46
    alinga
    0.44
     sw
    0.43
    SharedDtor
    0.42
    CDM
    0.42
    SqlClient
    0.41
    Activations Density 0.223%

    No Known Activations