© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10902
    Prev
    Next
    INDEX
    Explanations

    words used in scientific or biological taxonomy, particularly names of species and classifications.

    oai_token-act-pair · gemini-2.0-flash

    species/scientific classification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     ſta
    -1.14
     Theſe
    -1.10
     faſt
    -1.10
     purpoſe
    -1.09
     ſche
    -1.06
     whoſe
    -1.05
     ſtate
    -1.05
     raiſ
    -1.01
     tranſ
    -1.01
     ſen
    -1.00
    POSITIVE LOGITS
     nakalista
    0.59
     kasarigan
    0.58
     peix
    0.50
    IUCN
    0.49
     dAtA
    0.48
     pygame
    0.48
    EDEFAULT
    0.47
    createCanvas
    0.47
     AttributeSet
    0.47
    EObject
    0.47
    Activations Density 2.175%

    No Known Activations