© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15075
    Prev
    Next
    INDEX
    Explanations

    words related to scientific biological species

    oai_token-act-pair · gemini-2.0-flash

    species

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     species
    -1.13
     Species
    -0.98
    species
    -0.93
     SPECIES
    -0.92
    Species
    -0.91
     espèce
    -0.81
     espèces
    -0.77
     especies
    -0.76
    espèce
    -0.73
    SPECIES
    -0.73
    POSITIVE LOGITS
     kaarangay
    0.56
     ویکی‌پدی
    0.55
    DoubleQuotes
    0.55
    protoimpl
    0.51
    :]:
    0.49
     дописавши
    0.49
     doGet
    0.49
     transférez
    0.48
    InjectAttribute
    0.48
    awtextra
    0.48
    Activations Density 54.200%

    No Known Activations