© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5183
    Prev
    Next
    INDEX
    Explanations

    the word "species" and nearby words relating to biology with a slight preference for the word "species" by itself

    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_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    -2.63
     Species
    -2.33
    species
    -2.22
    Species
    -2.08
     SPECIES
    -1.99
     espèces
    -1.79
     especies
    -1.66
     espécies
    -1.66
     specie
    -1.64
    SPECIES
    -1.63
    POSITIVE LOGITS
    ,
    0.50
    โ
    0.47
    <sup>
    0.47
     lòng
    0.47
     inilah
    0.46
     szem
    0.45
    netbeans
    0.42
     —
    0.42
    burg
    0.42
    션
    0.41
    Activations Density 0.714%

    No Known Activations